NLP Wiki nlp https://jlab.soe.ucsc.edu/nlp-wiki/ 2026-05-10T14:39:09+00:00 NLP Wiki https://jlab.soe.ucsc.edu/nlp-wiki/ https://jlab.soe.ucsc.edu/nlp-wiki/lib/tpl/dokuwiki/images/favicon.ico text/html 2025-10-17T21:56:42+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:abstract_meaning_representation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:abstract_meaning_representation&rev=1760738202&do=diff Abstract Meaning Representation Introductions and Overviews * Introduction The best introduction to AMR. * AMR website * Banarescu et al 2013 - Abstract Meaning Representation for Sembanking * AMR Annotation * AMR Dict List of linguistic phenomena and how to handle them in AMR * AMR Bibliography * Generation * Hao et al 2022 - A Survey : Neural Networks for AMR-to-Text * Applications * Wein & Opizt - A Survey of AMR Applications Papers See an updated list of AMR pap… text/html 2025-06-21T01:54:02+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:agi https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:agi&rev=1750470842&do=diff Artificial General Intelligence (AGI) Overviews * Feng et al 2024 - How Far Are We From AGI: Are LLMs All We Need? Papers * Hart & Goertzel 2008 - OpenCog: A Software Framework for Integrative Artificial General Intelligence * Adams et al 2012 - Mapping the Landscape of Human-Level Artificial General Intelligence Good overview from 2012 * Michael et al 2022 - What Do NLP Researchers Believe? Results of the NLP Community Metasurvey (Contains questions about AGI) * Altmeyer et al 202… text/html 2025-06-03T00:26:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:alignment https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:alignment&rev=1748910391&do=diff Alignment (AI) Overviews * Shen et al 2023 - Large Language Model Alignment: A Survey * Ji et al 2023 - AI Alignment: A Comprehensive Survey * Anwar et al 2024 - Foundational Challenges in Assuring Alignment and Safety of Large Language Models Blog Posts, etc * 2022 - What Everyone in Alignment is Doing and Why Papers * Sun et al 2023 - Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision Wow, like the three laws of Asimov * Zhou et al … text/html 2024-09-07T01:04:37+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:ambiguity_in_language https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:ambiguity_in_language&rev=1725671077&do=diff Ambiguity Papers on Ambiguity * Stengel-Eskin et al 2023 - Zero and Few-shot Semantic Parsing with Ambiguous Inputs * Li et al 2024 - A Taxonomy of Ambiguity Types for NLP text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:amr_annotation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:amr_annotation&rev=1686814574&do=diff AMR Annotation This page describes how to annotate English sentences with AMR graphs to create more training data (perhaps in a new domain) or check the output of your parser. * Step 1: Read the guidelines to learn how AMR works: AMR Guidelines * Step 2: Watch the video on how to use the AMR editor: text/html 2023-07-06T00:58:19+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:ancient_languages https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:ancient_languages&rev=1688605099&do=diff Ancient Languages Papers * Latin BERT Bamman and Burns (2020) * Ancient Greek (AG) BERT by Singh et al. (2021) * Riemenschneider & Frank 2023 - Exploring Large Language Models for Classical Philology Related Pages * Computational Linguistics text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:argumentative_text_understanding https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:argumentative_text_understanding&rev=1686814574&do=diff Argumentative Text Understanding Also known as argument mining, see here. Papers See references here. Workshops and Shared Tasks * Workshop on Argument Mining (ArgMining): 2022 2021 2020 2019 2018 2017 (proceedings) 2016 2015 2014 * Argumentative Text Understanding for AI Debater (NLPCC2021) text/html 2025-04-04T23:53:18+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:attention_mechanisms https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:attention_mechanisms&rev=1743810798&do=diff Attention Mechanisms Overviews * Attention? Attention! Blog post by Weng * Brief Introduction to Attention Models * Chaudhari et al 2019 - An Attentive Survey of Attention Models Summary of Attention Mechanisms From Attention? Attention! Blog post by Weng: Key Papers * Graves 2013 - Generating Sequences With Recurrent Neural Networks Uses an alignment mechanism for handwriting generation, similar to the attention mechanism. The Deep Learning Book p. 415 at the end of Ch 10 says “… text/html 2023-09-06T12:12:17+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:authorship_attribution https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:authorship_attribution&rev=1694002337&do=diff Authorship Attribution Problem statement: Given a document, who wrote it? (Both closed-set and open-set versions.) People * Efstathios Stamatatos text/html 2024-08-06T23:04:39+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:automatic_essay_grading https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:automatic_essay_grading&rev=1722985479&do=diff Automatic Essay Grading Also known as Automatic Essay Scoring (AES). Overviews * Ramesh & Sanampudi 2021 - An Automated Essay Scoring Systems: A Systematic Literature Review * Shermis et al 2010 - Automated Essay Scoring: Writing Assessment and Instruction * Dikli 2006 - An Overview of Automated Scoring of Essays Papers * Han et al 2023 - FABRIC: Automated Scoring and Feedback Generation for Essays * Stahl et al 2024 - Exploring LLM Prompting Strategies for Joint Essay Scoring and… text/html 2024-07-02T23:46:40+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:automatic_fact_checking https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:automatic_fact_checking&rev=1719964000&do=diff Fact Checking Automatic Fact Checking Overviews See ACL Anthology - Automatic Fact Checking. * Thorne & Vlachos 2018 - Automated Fact Checking: Task Formulations, Methods and Future Directions * Popular media: 2019 - Understanding the Promise and Limits of Automated Fact-Checking * Kotonya & Toni 2020 - Explainable Automated Fact-Checking: A Survey * Gu et al 2021 - A Survey on Automated Fact-Checking * Das et al 2023 - The State of Human-centered NLP Technology for Fact-checking … text/html 2026-03-05T00:02:27+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:autonomous_language_agents https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:autonomous_language_agents&rev=1772668947&do=diff Autonomous Language Agents LLM agents, etc. Overviews * See the related work of Chen 2023 for a nice overview. * Wang et al 2023 - A Survey on Large Language Model based Autonomous Agents * LLM Agent Survey (github) - from the above survey, continuously updated * Li et al 2025 - A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning * LLM Agent Survey (github) - from the above survey, continuously updated * Xi et al 2023… text/html 2025-05-23T07:16:22+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:autonomous_scientific_research https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:autonomous_scientific_research&rev=1747984582&do=diff Autonomous Scientific Research Papers * 2025 - NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification text/html 2024-08-25T23:53:04+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:beam_search https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:beam_search&rev=1724629984&do=diff Beam Search For an introduction, see Wikipedia - Beam Search. Papers * Beam search for RNNs: Rush et al 2015 - A Neural Attention Model for Abstractive Sentence Summarization This may be the first paper to use beam search in seq2seq models (as far as Jeff knows) * Goyal et al 2017 - A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models History Invented for decoding in speech recognition, beam search was the de-facto decoding algorithm for statistical … text/html 2023-07-06T00:22:40+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:bert_and_friends https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:bert_and_friends&rev=1688602960&do=diff BERT Introductions to BERT * Paper: Devlin et al 2018 - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding * Blogs * Demystifying BERT: A Comprehensive Guide to the Groundbreaking NLP Framework * The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) * Textbooks * SLP Ch 11 (especially 11.2) * Training from scratch * Izsak et al 2021 - How to Train BERT with an Academic Budget * Retrospective Analyssis * Nityasya et al… text/html 2025-05-14T18:36:46+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:bias https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:bias&rev=1747247806&do=diff Bias Bias (Fairness, Society and Ethics) Bias in General * Overviews * Meade et al 2021 - An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models * Papers * Schick et al 2021 - Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP In Large Language Models * Gupta et al 2023 - Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs Gender Bias * Overviews * Sun et al 2019 - Mitigating Gende… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:brittleness_in_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:brittleness_in_nlp&rev=1686814574&do=diff See Robustness in NLP. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:causality https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:causality&rev=1686814574&do=diff Causality Definition * The best operational definition for annotating causality in text comes from this paper: Ikuta 2014 * The definition is X CAUSES Y “if, according to the writer, the particular EVENT Y was inevitable given the particular EVENT X.” text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:cfgs_and_scfgs https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:cfgs_and_scfgs&rev=1686814574&do=diff CFGs and SCFGs Algorithms * Intersecting a CFG with a regular language * Hanneforth 2011 - A Practical Algorithm for Intersecting Weighted Context-free Grammars with Finite-State Automata * Common to use the Bar-Hillel construction, see here Recent Applications * Shaw et al 2021 - Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?. Uses NQG (Neural Quasi-Synchronous Grammar) * Shin et al 2021 - Constrained Language Models Yi… text/html 2025-03-07T11:21:11+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:chatbots https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:chatbots&rev=1741346471&do=diff Chatbots Overviews * Dam et al 2024 - A Complete Survey on LLM-based AI Chatbots LLM-Based Chatbots * System descriptions * LaMDA: Language Models for Dialog Applications According to Dam 2024, this is the basis for Google's Bard and Gemini * Bai et al 2022 - Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback Anthropic's chatbot Evaluation * Overviews * Finch & Choi 2020 - Towards Unified Dialogue System Evaluation: A Comprehensive Ana… text/html 2025-06-20T20:50:04+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:chatgpt https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:chatgpt&rev=1750452604&do=diff ChatGPT Overviews * Liu et al 2023 - Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models Papers * Evaluations on Benchmarks * Bang et al 2023 - A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity * Laskar et al 2023 - A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets (ACL 2023) * Impact of ChatGPT * Estimating Prevalence of Usage * Kobak et al … text/html 2024-06-03T13:28:18+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:code_switching https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:code_switching&rev=1717421298&do=diff Code Switching Code switching is when words from more than one language (usually two languages) are used in the same sentence. Overviews * Sitaram et al 2019 - A Survey of Code-switched Speech and Language Processing * Winata et al 2023 - The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges Papers * Lee & Wang 2015 - Emotion in Code-switching Texts: Corpus Construction and Analysis * Mendels et al 2018 - Collecting Code-Switched Data f… text/html 2023-07-25T01:07:34+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:commonsense_reasoning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:commonsense_reasoning&rev=1690247254&do=diff Commonsense Reasoning Papers General Papers * Singh 2002 - The Public Acquisition of Commonsense Knowledge The Open Mind Common Sense project, which was the foundation of ConceptNet * Angeli & Manning 2014 - NaturalLI: Natural Logic Inference for Common Sense Reasoning * Speer et al 2016 - ConceptNet 5.5: An Open Multilingual Graph of General Knowledge * Zellers et al 2018 - SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference * Zellers et al 2019 - HellaSwag:… text/html 2023-07-07T18:21:25+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:compositional_generalization https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:compositional_generalization&rev=1688754085&do=diff Compositional Generalization Overviews * Lin et al 2023 - A Survey on Compositional Generalization in Applications Not an NLP paper, and not very comprehensive. WARNING: Missing a bunch of NLP work. Papers * SCAN dataset: Lake & Baroni 2017 - Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks * Chang et al 2018 - Automatically Composing Representation Transformations as a Means for Generalization Has a good section on what comp… text/html 2023-07-06T00:55:46+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:computational_linguistics https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:computational_linguistics&rev=1688604946&do=diff Computational Linguistics Various papers on computational linguistics, that is the study of language (linguistics) using computers. Areas of Linguistics * Philology * Riemenschneider & Frank 2023 - Exploring Large Language Models for Classical Philology Related Pages * Ancient Languages text/html 2023-07-03T19:00:00+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:constituency_parsing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:constituency_parsing&rev=1688410800&do=diff Constituency Parsing Supervised Constituency Parsing See also NLP Progress - Constituency parsing CKY Parsing * General Papers * See also Wikipedia - CYK algorithm * Semi-ring parsing, see also Semiring * Goodman 1999 * Hypergraph parsing, see also Hypergraphs * Klein & Manning 2001 - Parsing and Hypergraphs * Huang 2008 - Advanced Dynamic Programming in Semiring and Hypergraph Frameworks * Extensions * Generalized CKY (CKY+). Handles grammars not in CNF form (hand… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:controlled_language https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:controlled_language&rev=1686814574&do=diff Controlled Language Overviews * 2014 - A Survey and Classification of Controlled Natural Languages Papers * Cramer et al 2009 - The Naproche Project Controlled Natural Language Proof Checking of Mathematical Texts Attempto Controlled English (ACE) From Diller 2019: Main site: Attempto Project. See also Wikipedia - Attempto Controlled English. For more papers see Attempto Publications. * Fuchs et al 2008 - Attempto Controlled English for Knowledge Representation * Diller e… text/html 2025-05-16T04:54:36+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:copyright_issues https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:copyright_issues&rev=1747371276&do=diff Copyright Issues Papers * 2023 - Copyright Violations and Large Language Models * Chen et al 2024 - CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation Related Pages * Privacy * LLMs - Copyright Issues text/html 2024-01-04T23:21:15+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:coreference_resolution https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:coreference_resolution&rev=1704410475&do=diff Coreference Resolution See also NLP Progress - Coreference Resolution. Surveys * Stylianou & Vlahavas 2019 - A Neural Entity Coreference Resolution review * Anaphora review: Sukthanker et al 2018 - Anaphora and coreference resolution: A review Papers * Neural Methods * Clark 2016 (Kevin Clark's preliminary work) * Clark & Manning 2016 - Improving Coreference Resolution by Learning Entity-Level Distributed Representations * Clark & Manning 2016 - Deep Reinforcement Learning fo… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:corpus_analysis https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:corpus_analysis&rev=1686814574&do=diff Corpus Analysis Often considered a linguistics topic, corpus analysis is the study of language in a corpus, often analyzing the distribution of various phenomena (phonological, lexical, syntactic, etc). Sometimes the analysis is performed comparing across time, languages, or different genres. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:cross-lingual_transfer https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:cross-lingual_transfer&rev=1686814574&do=diff Cross-Lingual Transfer Papers * Artetxe et al 2018 - A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well talk * Garneau et al 2020 - A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well * Laser: Artetxe & Schwenk 2019 - Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Bey… text/html 2025-03-27T19:42:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:crowdsourcing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:crowdsourcing&rev=1743104551&do=diff Crowdsourcing Resources * Tutorials * NAACL 2021 Tutorial - Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial video Great tutorial * EMNLP 2021 tutorial: slides * LLM Labeling w/ Human in the Loop tutorial proposal: 2024 - Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop * Platforms * Amazon Mechanical Turk * Appen (was called Crowdflower, then Figure-Eight, then aquired by Appen) text/html 2023-11-29T21:14:21+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:datasets https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:datasets&rev=1701292461&do=diff NLP Datasets See also NLP Progress, Wikipedia List of datasets, and nlp-datasets. Also data preparation. Language Modeling Corpora * BNC corpus * Gigaword * Common crawl * Bookcorpus (Used in BERT) General Benchmarks or Multi-Task Benchmarks * GLUE: paper - Warning: Has an issue with QQP and WNLI due to dev and tests sets not coming from the same distribution. See text/html 2023-12-10T06:18:06+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:dataset_creation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:dataset_creation&rev=1702189086&do=diff Dataset Creation Annotation For annotation tools, see Software - Annotation Tools. Annotation can often be greatly sped up by building your own annotation tool with exactly the features you want for your application. This is can be a worthwhile time investment, since a well-designed tool can speed up annotation. text/html 2025-05-21T19:53:47+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:data_augmentation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:data_augmentation&rev=1747857227&do=diff Data Augmentation in NLP Overviews * Feng et al 2021 - A Survey of Data Augmentation Approaches for NLP Papers * Shen et al 2020 - A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation Synthetic Data Augmentation or Generation * Jia & Liang 2016 - Data Recombination for Neural Semantic Parsing * Andreas 2019 - Good-Enough Compositional Data Augmentation GECA method * Guo et al 2020 - Sequence-Level Mixed Sample Data Augmentation … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:data_preparation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:data_preparation&rev=1686814574&do=diff Data Preparation Creating a Train/Dev/Test Split Generally, you'll want use an existing train/dev/test split if it exists for that dataset so you can compare to previous methods. If the dataset doesn't have a split, it may not be a standard NLP dataset and it may be better to use a different dataset that is more widely used in experiments. If you need to create your train/dev/test split, here are some things to consider: text/html 2024-08-25T23:53:21+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:decoding https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:decoding&rev=1724630001&do=diff Decoding In structured prediction and NLP, decoding refers to predicting the output given the input. For example, the input could be a sentence, and the output could be a sequence of part-of-speech tags. In this case, decoding is predicting the POS tags given the input sentence. The decoding algorithm is the algorithm used to make the predictions (such as dynamic programming, $Y$$X$ text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:deep_latent_variable_models https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:deep_latent_variable_models&rev=1686814574&do=diff Deep Latent Variable Models Deep latent variable models are deep neural networks models that have latent variables (latent random variables - that is, unobserved random variables). Papers * Havrylov et al 2019 - Cooperative Learning of Disjoint Syntax and Semantics Latent variable model that learns a latent parse tree for the ListOps dataset. (cited from text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:dependency_parsing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:dependency_parsing&rev=1686814574&do=diff Dependency Parsing See also NLP Progress - Dependency Parsing Graph-Based Dependency Parsing Early papers (pre-neural): * The paper that started graph-based dependency parsing: McDonald et al 2005 - Non-projective Dependency Parsing using Spanning Tree Algorithms * Koo & Collins 2010 - Efficient Third-order Dependency Parsers Neural graph-based dependency parsing * Pei et al 2015 - An Effective Neural Network Model for Graph-based Dependency Parsing * Kiperwasser & Goldberg 2016 - … text/html 2024-09-04T00:27:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:dialog https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:dialog&rev=1725409651&do=diff Dialog Overviews Best overviews: Chen et al 2017 - A Survey on Dialogue Systems: Recent Advances and New Frontiers and Roller et al 2020 - Recipes for building an open-domain chatbot. * Introductions * S&LP - Ch 24 * General * Chen et al 2017 - A Survey on Dialogue Systems: Recent Advances and New Frontiers * Gao et al 2018 - Neural Approaches to Conversational AI (95 pages) * Roller et al 2020 - Open-Domain Conversational Agents: Current Progress, Open Problems, and Future D… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:diarization https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:diarization&rev=1686814574&do=diff Diarization See Wikipedia - Speaker Diarisation Overviews * Park et al 2021 - A Review of Speaker Diarization: Recent Advances with Deep Learning Related Pages * Dialog text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:discourse_analysis https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:discourse_analysis&rev=1686814574&do=diff Discourse Analysis Introductions and Overviews * Introductions * S&LP - Ch 22 * Overviews * 2013 - Multiparticipant chat analysis: A survey * PDTB * Prasad et al 2014 - Reflections on the Penn Discourse TreeBank, Comparable Corpora, and Complementary Annotation Discourse Parsing * Marcu & Echihabi 2002 - An Unsupervised Approach to Recognizing Discourse Relations The first discourse parser * Li et al 2014 - Recursive Deep Models for Discourse Parsing * Afantenos et al… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:domain_adaptation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:domain_adaptation&rev=1686814574&do=diff Domain Adaptation See Wikipedia - Domain Adaptation. Usually in NLP, domain adaptation becomes necessary if the training data is from a different genre than the testing data - you train on newswire, test on medical domain, for example. Since natural language is so varied, often the domains are quite different, with different lexical items, syntactic patterns, and semantics. For a definition of what a domain is, see text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:entailment https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:entailment&rev=1686814574&do=diff Entailment General Entailment Papers * Evans et al 2018 - Can Neural Networks Understand Logical Entailment? Recognizing Textual Entailment RTE, also know as natural language inference (NLI). Papers * Bowman et al 2015 - A large annotated corpus for learning natural language inference SNLI dataset * ESIM model: Chen et al 2016 - Enhanced LSTM for Natural Language Inference Famous model, the best pre-BERT NLI model * Williams et al 2017 - A Broad-Coverage Challenge Corpus for Senten… text/html 2025-06-06T23:29:07+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:entity_linking https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:entity_linking&rev=1749252547&do=diff Entity Linking Overviews * Introduction: Eisenstein p. 406 * Shen et al 2015 - Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions * Section 4.2 of Singh 2018 * Sevgili et al 2020 - Neural Entity Linking: A Survey of Models Based on Deep Learning Papers See ACL Anthology - Entity linking * Lin et al 2012 - Entity Linking at Web Scale * Rao et al 2014 - Entity Linking: Finding Extracted Entities in a Knowledge Base Explains why it's good to use a ranking app… text/html 2023-10-06T17:25:20+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:ethics https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:ethics&rev=1696613120&do=diff Ethics in NLP In March 2020, ACL adopted the ACM code of ethics. Papers about Ethics * Hovy & Spruit (2016). The Social Impact of Natural Language Processing * Leidner & Plachouras 2017 - Ethical by Design: Ethics Best Practices for Natural Language Processing * Paper discussing Chen et al 2019: Leins et al 2020 - Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis? * Williams et al 2023 - Voice in the Machine: Ethical Consider… text/html 2025-11-18T22:24:06+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:evaluation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:evaluation&rev=1763504646&do=diff Evaluation Natural Language Output To evaluate natural language output, researchers often use BLEU or human evaluation. For summarization, they often use ROUGE. See also Generation - Evaluation, Machine Translation - Evaluation, and Dialog - Evaluation. Papers * Rodriguez et al 2021 - Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards? Evaluation with Large Language Models text/html 2023-07-06T01:33:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:event_extraction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:event_extraction&rev=1688607194&do=diff Event Extraction Overviews * Xiang & Wang 2019 - A Survey of Event Extraction From Text * Zhang et al 2018 - A Survey of Open Domain Event Extraction Papers * Chambers & Jurafsky 2011 - Template-Based Information Extraction without the Templates * McClosky et al 2011 - Event Extraction as Dependency Parsing * Du & Cardie 2020 - Event Extraction by Answering (Almost) Natural Questions Unsupervised * Chambers & Jurafsky 2011 - Template-Based Information Extraction without the Tem… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:event_semantics https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:event_semantics&rev=1686814574&do=diff Event Semantics * Durative * Habitual * Stative vs non-stative Related Pages * Causality * Modality * Time text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:experimental_method https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:experimental_method&rev=1686814574&do=diff Experimental Method and Reproducibility Reproducibility * Gundersen & Kjensmo 2018 - State of the Art: Reproducibility in Artificial Intelligence * 2017 - A Manifesto for Reproducible Science Nice overview here * Dodge et al 2019 - Show Your Work: Improved Reporting of Experimental Results Introduces reproducibility checklists, see below, and also give a procedure for estimating if one model is better than another at various hyper-parameter tuning budgets ( text/html 2025-06-01T23:17:09+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:explainability https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:explainability&rev=1748819829&do=diff Explainability Explainability can be crucial for the adoption of automatic methods. For example, without an explaination for the diagnosis, doctors are highly unlikely to use an automatic diagnosis system. Explainability is an open problem for machine learning and NLP (see text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:factivity https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:factivity&rev=1686814574&do=diff See Epistemic Modality text/html 2023-07-06T01:08:39+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:financial_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:financial_nlp&rev=1688605719&do=diff Financial NLP Papers * Shah et al 2023 - Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis Datasets * Shah et al 2023 - Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis text/html 2025-05-01T10:53:17+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:forecasting https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:forecasting&rev=1746096797&do=diff Forecasting Using NLP methods to predict aspects of the future. Papers * Li & Flanigan 2024 - Future Language Modeling from Temporal Document History * Nako & Jatowt 2025 - Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction Related Pages * Event Simulation * Text-Driven Forecasting text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:formal_grammar https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:formal_grammar&rev=1686814574&do=diff Formal Grammar String Grammars * See CFGs and SCFGs Tree Grammars Graph Grammars * Gilroy et al 2017 - (Re)introducing Regular Graph Languages * Chiang et al 2018 - Weighted DAG Automata for Semantic Graphs text/html 2023-11-30T05:53:51+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:fsas_and_fsts https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:fsas_and_fsts&rev=1701323631&do=diff FSAs and FSTs Overviews * Finite state automata (FSAs) * Wikipedia - Finite-State Machine * Lecture: NLP 201 2020 - Oct 8 * Finite state transducers (FSTs) * Wikipedia - Finite-State Transducer Papers * Argueta & Chiang 2017 - Decoding with Finite-State Transducers on GPUs * Argueta & Chiang 2018 - Composing Finite State Transducers on GPUs * Suresh et al 2019 - Distilling Weighted Finite Automata from Arbitrary Probabilistic Models Talks about converting a neural langua… text/html 2023-11-15T05:07:13+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:future_directions https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:future_directions&rev=1700024833&do=diff Future Directions Papers * Saphra et al 2023 - First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:gamification https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:gamification&rev=1686814574&do=diff Gamification Papers * Eisenschlos et al 2021 - Fool Me Twice: Entailment from Wikipedia Gamification github Related Pages * Crowdsourcing text/html 2024-08-16T00:57:59+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:generation&rev=1723769879&do=diff Natural Language Generation Overviews * Introduction: Eisenstein p. 457 * Gatt et al 2017 - Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation Now outdated. Goes over traditional non-neural methods. * Yu et al 2020 - A Survey of Knowledge-Enhanced Text Generation Data-to-Text Data-to-text generation is generation where the input is formatted data such as tables of numbers. A typical example is generating human-readable weather report… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:grammatical_error_correction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:grammatical_error_correction&rev=1686814574&do=diff Grammatical Error Correction Also known as “automatic grammar checking.” Overviews * Dale & Viethen 2021 - The Automated Writing Assistance Landscape in 2021 Papers * Junczys-Dowmunt et al 2017 - Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task * Grundkiewicz et al 2019 - Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data * Lichtarge et al 2019 - Corpora Generation for Grammatical Error Correction Pa… text/html 2025-04-01T21:03:22+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:grounded_language_learning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:grounded_language_learning&rev=1743541402&do=diff Grounded Language Learning Papers * Kollar et al 2013 - Toward Interactive Grounded Language Acquisition * Krishnamurthy & Kollar 2013 - Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World * Hermann et al 2017 - Grounded Language Learning in a Simulated 3D World (See * Yu et al 2018 - Interactive Grounded Language Acquisition and Generalization in a 2D World People * Jayant Krishnamurthy (older work, no longer working in NLP) Related Pages … text/html 2025-09-19T21:06:27+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:grounding https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:grounding&rev=1758315987&do=diff Grounding Papers * In Dialog * Madureira & Schlangen 2024 - It Couldn’t Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning * LLMs and Grounding * Shaikh et al 2025 - Navigating Rifts in Human-LLM Grounding: Study and Benchmark * Alternative Ideas on Grounding * McAllester 2022 - The Case Against Grounding Related Pages * Grounded Language Learning * Vision and Language text/html 2025-06-02T00:52:44+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:hallucination_and_factivity https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:hallucination_and_factivity&rev=1748825564&do=diff Hallucination and Factivity Overviews * In Generation * Ji et al 2022 - Survey of Hallucination in Natural Language Generation * In Large Language Models * Zhang et al 2023 - Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models * Rawte et al 2023 - A Survey of Hallucination in Large Foundation Models * Ye et al 2023 - Cognitive Mirage: A Review of Hallucinations in Large Language Models * Andriopoulos & Pouwelse 2023 - Augmenting LLMs with Knowle… text/html 2024-10-24T18:40:20+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:hci_and_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:hci_and_nlp&rev=1729795220&do=diff HCI and NLP NLP papers that are HCI focused or in HCI conferences. Papers * Lawley 2023 - VAL: Interactive Task Learning with GPT Dialog Parsing Related Pages * Human-In-The-Loop text/html 2024-02-20T09:05:36+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:history_of_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:history_of_nlp&rev=1708419936&do=diff History of NLP Historical Surveys * Zechner 1997 - A Literature Survey on Information Extraction and Text Summarization Papers and Popular Descriptions * Statistical NLP * Church 1988 - A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text One of the first statistical POS taggers, one of the papers that started the statistical/machine learning revolution in NLP * [Charniak 1998 - Statistical Techniques for NLP] Early Work (prior to 2000) text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:hmm https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:hmm&rev=1686814574&do=diff Hidden Markov Models Basics * HMMs vs CRFs: See Liang & Jordan 2008 - An Asymptotic Analysis of Generative, Discriminative, and Pseudolikelihood Estimators especially table 2, and summary slide 44 here Applications in MT * Vogel et al 1996 - HMM-Based Word Alignment in Statistical Translation * Wang et al 2018 - Neural Hidden Markov Model for Machine Translation Recent Advances * Chiu & Rush 2020 - Scaling Hidden Markov Language Models Scaling the number of hidden states to 2^15 st… text/html 2025-05-31T07:43:09+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:human-in-the-loop https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:human-in-the-loop&rev=1748677389&do=diff Human-In-The-Loop, RLHF and Interactive Methods Overviews See also Interactive NLP Workshop - References and Awesome RLHF * Wang et al 2021 - Putting Humans in the Natural Language Processing Loop: A Survey * Blog posts * HuggingFace - Illustrating Reinforcement Learning from Human Feedback (RLHF) General Papers * Ribeiro & Lundberg 2022 - Adaptive Testing and Debugging of NLP Models * Interactive AI Model Debugging and Correction (2022 Thesis) (talk) * InstructGPT: Ouyang et … text/html 2024-05-24T04:07:03+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:humor_detection_and_generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:humor_detection_and_generation&rev=1716523623&do=diff Humor Detection and Generation Detection Generation * Tikhonov & Shtykovskiy et al 2024 - Humor Mechanics: Advancing Humor Generation with Multistep Reasoning text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:hypergraphs https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:hypergraphs&rev=1686814574&do=diff Hypergraphs Hypergraphs are a generalization of graphs, where the edges can connect any number of nodes (1 or more nodes). There can be directed and undirected edges in a hypergraph. In a directed edge, some of the edges are marked as the head, and the others are the tail. Hypergraphs have been used extensively in NLP for parsing or machine translation with grammars. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:image_captioning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:image_captioning&rev=1686814574&do=diff Image and Video Captioning Overviews * Image captioning * Hossain et al 2018 - A Comprehensive Survey of Deep Learning for Image Captioning * Sharma et al 2020 - Image Captioning: A Comprehensive Survey * Video captioning * Apostolidis et al 2021 - Video Summarization Using Deep Neural Networks: A Survey Image Captioning See also this bibliography. * Lu et al 2018 - Neural Baby Talk Video Captioning * Venugopalan et al 2014 - Translating Videos to Natural Language Using… text/html 2025-01-17T20:39:10+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:information_extraction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:information_extraction&rev=1737146350&do=diff Information Extraction Overviews * Introduction: Eisenstein p. 403 * Sarawagi 2008 - Information Extraction Old but good introduction * Grishman 2015 - Information Extraction * Mannai et al 2017 - Information Extraction Approaches: A Survey (Springer link) * Golshan et al 2018 - A Study of Recent Contributions on Information Extraction (Not so great overview) * Singh 2018 - Natural Language Processing for Information Extraction Best overview * Weischedel & Boschee 2018 - What C… text/html 2025-07-07T06:00:33+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:information_retrieval https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:information_retrieval&rev=1751868033&do=diff Information Retrieval With the advent to deep learning models, there is a lot of new work to be done in the area of information retrieval (IR). See below for examples. Overviews * Azad & Deepak 2017 - Query Expansion Techniques for Information Retrieval: A Survey Papers * Yu et al 2021 - PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer * Naseri et al 2021 - CEQE: Contextualized Embeddings for Query Expansion * Gao et al 2021 - COIL: Revisit Exact Lexical Match in Infor… text/html 2025-06-01T22:58:13+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:instruction-tuning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:instruction-tuning&rev=1748818693&do=diff Instruction Tuning Overviews * Instruction-Tuning Papers * Zhang et al 2023 - Instruction Tuning for Large Language Models: A Survey Papers * Mishra et al 2021 - Cross-Task Generalization via Natural Language Crowdsourcing Instructions * Wei et al 2021 - Finetuned Language Models Are Zero-Shot Learners * Multitask Prompted Training Enables Zero-Shot Task Generalization * ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization * InstructGPT … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:integer_linear_programming https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:integer_linear_programming&rev=1686814574&do=diff Integer Linear Programming Integer linear programs (ILPs) have been used to solve NP-hard decoding algorithms in NLP. They have been used in dependency parsing, coreference resolution, summarization, and many others. Often, ILP formulations are used to solve a decoding problem exactly before a specialized algorithm has been developed (for an example, see text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:intelligent_tutor https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:intelligent_tutor&rev=1686814574&do=diff Intelligent Tutor Papers * Pradhan et al 2016 - My Science Tutor—Learning Science with a Conversational Virtual Tutor * [Ward et al 2019 - My Science Tutor and the MyST Corpus] * MyST corpus download * [Suresh et al 2019 - Automating Analysis and Feedback to Improve Mathematics Teachers’ Classroom Discourse] * Ganesh et al 2021 - What Would a Teacher Do? Predicting Future Talk Moves * Suresh et al 2021 - Using Transformers to Provide Teachers with Personalized Feedback on their C… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:interpretability https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:interpretability&rev=1686814574&do=diff See Explainability text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:jeff_s_list_of_interesting_papers https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:jeff_s_list_of_interesting_papers&rev=1686814574&do=diff Jeff's List of Interesting Papers * Old papers * Shank 1975 - SAM — A Story Understander * Granger 1977 - FOUL-UP: A Program that Figures Out Meanings of Worcds from Context Really cool work. Uses “knowledge embodied in scripts to figure out likely definitions for unknown words.” Related to recent (2020s) work in common-sense reasoning. * Papers by Jason Weston (mostly dialog papers) text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:keyphrase_generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:keyphrase_generation&rev=1686814574&do=diff Keyword and Keyphrase Generation Papers * Rake algorithm: Rose et al 2010 - Automatic keyword extraction from individual documents Widely used unsupervised keyword extraction algorithm * Suzuki & Takatsuka 2016 - Extraction of Keywords of Novelties From Patent Claims * 2021 - An Empirical Study on Neural Keyphrase Generation Related Pages * Summarization text/html 2023-11-29T20:58:02+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:key_papers_in_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:key_papers_in_nlp&rev=1701291482&do=diff Key Papers in NLP Work in progress. Aims to be a compact list of the key papers in NLP. Overviews * Machine Translation * Dialog * Question Answering * Information Extraction * Deep Learning * Ruder's 2016 paper Historical Background text/html 2025-02-24T06:59:43+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:knowledge-enhanced_methods https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:knowledge-enhanced_methods&rev=1740380383&do=diff Knowledge-Enhanced Methods in NLP Overviews * Yu et al 2022 - A Survey of Knowledge-Enhanced Text Generation * Wei et al 2021 - Knowledge Enhanced Pretrained Language Models: A Comprehensive Survey * Hu et al 2022 - A Survey of Knowledge Enhanced Pre-trained Language Models Papers General Papers * Raman et al 2020 - Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation Knowledge-Grounded Question Answering * Lin et al 2019 - KagNet: Knowledge-Aware Graph… text/html 2025-05-31T07:49:55+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:knowledge_editing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:knowledge_editing&rev=1748677795&do=diff Knowledge Editing Papers * Meng et al 2022 - Locating and Editing Factual Associations in GPT Introduces ROME * Meng at el 2022 - Mass-Editing Memory in a Transformer Follow-up work of Meng 2022 allowing editing many facts at once. Great paper. Also shows that factual knowledge is distributed in the MLP layers * Wang et al 2025 - LoKI: Low-damage Knowledge Implanting of Large Language Models Connects mechanistic insights into LLM knowledge storage with editing. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:knowledge_extraction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:knowledge_extraction&rev=1686814574&do=diff Knowledge Extraction “Knowledge extraction” isn't a real NLP term, I just came up with it to classify these methods that extract some kind of knowledge from text: definitions, axiomatic knowledge, etc. Definitions * SemEval-2020 Task 6: Definition extraction from free text with the DEFT corpus Official task on codalab Scientific Knowledge text/html 2025-06-27T23:05:36+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:knowledge_graphs https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:knowledge_graphs&rev=1751065536&do=diff Knowledge Graphs Overviews * Knowledge Graphs * Nickel et al 2015 - A Review of Relational Machine Learning for Knowledge Graphs * Gi et al 2020 - A Survey on Knowledge Graphs: Representation, Acquisition and Applications * Knowledge Graph Completion * [A Survey on Knowledge Graph Embeddings for Link Prediction] * Arora 2020 - A Survey on Graph Neural Networks for Knowledge Graph Completion Knowledge Graph Construction See also Relation Extraction. * Dong et al 2020 - Au… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:label_bias_problem https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:label_bias_problem&rev=1686814574&do=diff Label Bias Problem Papers * Lafferty et al 2001 - Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data Introduced the label bias problem, which is present in Maximum-Entropy Markov Models (MEMMs) but not Conditional Random Fields (CRFs). This drawback of MEMMs was one of the main reasons for inventing CRFs * Murray & Chiang 2018 - Correcting Length Bias in Neural Machine Translation Argues that the beam search problem in NMT occurs because of the label… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:language_identification https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:language_identification&rev=1686814574&do=diff Language Identification Overviews * Jauhiainen et al 2018 - Automatic Language Identification in Texts: A Survey Methods and Papers * Lui & Baldwin 2012 - langid.py: An Off-the-shelf Language Identification Tool * Palakodety et al 2020- Hope Speech Detection: A Computational Analysis of the Voice of Peace Clustering based on polyglot word embeddings is an easy method for unsupervised language detection (see section 5.1). * Palakodety & KhudaBukhsh 2020 - Annotation Efficient Language… text/html 2026-03-07T22:21:26+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:language_model https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:language_model&rev=1772922086&do=diff Language Models Traditional definition of a language model (LM): a language model is a probability distribution over sentences, that is, it assigns probabilities to sentences. Language models can usually compute the probability of the next word given a sequence of words ( text/html 2025-10-08T08:46:10+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:language_to_programs https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:language_to_programs&rev=1759913170&do=diff Language to Programs General Program Synthesis See summary here (Sachan 2017) * Chen et al 2016 - Latent Attention For If-Then Program Synthesis * Yin & Neubig 2017 - A Syntactic Neural Model for General-Purpose Code Generation * Li et al 2022 - Competition-Level Code Generation with AlphaCode website blog post Treats competitive coding as seq2seq from problem description to code solution. Code Generation * AlphaCode: Li et al 2022 - Competition-Level Code Generation with AlphaCode … text/html 2025-10-10T09:05:36+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:large_reasoning_models https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:large_reasoning_models&rev=1760087136&do=diff Large Reasoning Models o1 or r1-style LLMs, often called “large reasoning models” (LRMs) (see Cuadron 2025) Overviews * Xu et al 2025 - Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models * Kumar et al 2025 - LLM Post-Training: A Deep Dive into Reasoning Large Language Models * Sui et al 2025 - Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Papers * Havrilla et al 2024 - Teaching Large Language Models to Reason wi… text/html 2025-04-30T20:32:15+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:learning_to_communicate https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:learning_to_communicate&rev=1746045135&do=diff Learning to Communicate There are some papers on artifical agents learning to communicate to play a game, etc. They either learn a language from scratch (an emergent language) or use reinforcement learning to improve an existing model of language. text/html 2024-06-28T03:25:49+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:legal_domain_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:legal_domain_nlp&rev=1719545149&do=diff Legal Domain NLP Overviews * Zhong et al 2020 - How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence * Nice overview of resources here: Samy et al 2020 - Legal-ES: A Set of Large Scale Resources for Spanish Legal Text Processing * Vogel et al 2017 - Computer Assisted Legal Linguistics: Corpus Analysis as a New Tool for Legal Studies Papers * Legal Document Classification * Nallapati & Manning 2008 - Legal Docket Classification: Where Machine Learning Stumb… text/html 2025-01-25T02:08:41+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:lifelong_learning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:lifelong_learning&rev=1737770921&do=diff Lifelong Learning Papers * Mitchell et al 2018 - Never-Ending Learning or Mitchell et al 2015 - Never-Ending Learning * Barrault et al 2020 - Findings of the First Shared Task on Lifelong Learning Machine Translation Links * Read the Web Project at CMU (NELL) * NELL: Never-Ending Language Learning * Wikipedia - Never-Ending Language Learning * WMT Shared Task * Lifelong Learning for Machine Translation Shared Task 2020 Related Pages * Continual Learning * Human-In-Th… text/html 2026-03-07T22:18:33+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:llm_safety https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:llm_safety&rev=1772921913&do=diff Large Language Model Safety Overviews * Huang et al 2023 - A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation * Liu et al 2023 - Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment * Dong et al 2024 - Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey * Shi et al 2024 - Large Language Model Safety: A Holistic Survey Great survey * 2025 - International AI Safety Repor… text/html 2025-08-30T00:33:47+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:logic_in_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:logic_in_nlp&rev=1756514027&do=diff Logic in NLP This page is about methods that use logic or logical forms in NLP. Papers * Mitra & Baral 2016 - Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning * Han et al 2022 - FOLIO: Natural Language Reasoning with First-Order Logic * Lalwani et al 2024 - NL2FOL: Translating Natural Language to First-Order Logic for Logical Fallacy Detection * Toroghi et al 2024 - Verifiable, Debuggable, and Repairable Commonsense … text/html 2024-05-15T06:39:10+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:low-resource_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:low-resource_nlp&rev=1715755150&do=diff Low-Resource NLP Overviews * Hedderich et al 2020 - A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios Papers * Garrette & Baldridge 2013 - Learning a Part-of-Speech Tagger from Two Hours of Annotation * Wang et al 2022 - PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks * Zhang et al 2022 - How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language * AfriBERTa: Ogueji et al 2021 - Small … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:lstm https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:lstm&rev=1686814574&do=diff LSTMs Bi-directional LSTMS Prior to Transformer models, Bi-LSTMs with max-pooling were a standard baseline model architecture. From Talman et al 2018 - Sentence Embeddings in NLI with Iterative Refinement Encoders: Conneau et al. (2017) With tweaks, they can outperform Transformer models. See Chen et al 2018 - The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation. Resources * Jeurgen's LSTM Tutorial text/html 2024-08-13T06:21:26+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:machine_translation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:machine_translation&rev=1723530086&do=diff Machine Translation Overviews For a reading list, see The Machine Translation Reading List * Philipp Koehn's 2017 Draft Chapter on NMT * Philipp Koehn's draft book on NMT * Philipp Koehn's 2020 Book - Neural Machine Translation * Stahlberg 2019 - Neural Machine Translation: A Review and Survey * Yang et al 2020 - A Survey of Deep Learning Techniques for Neural Machine Translation * Tan et al 2020 - Neural Machine Translation: A Review of Methods, Resources, and Tools Key Papers … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:medical_domain_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:medical_domain_nlp&rev=1686814574&do=diff Medical and Biomedical NLP Overviews * Ghoulam et al 2015 - Information Extraction in the Medical Domain * Hahn & Oleynik - Medical Information Extraction in the Age of Deep Learning Biomedical Datasets * Bio AMR Corpus Clinical Health Records “Clinical Health Records (CHRs) are documents where doctors take notes on a patient’s medical condition, his or her progress, and suggest possible medication and treatment text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:mental_health_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:mental_health_nlp&rev=1686814574&do=diff NLP for Mental Health Papers * Ziems et al 2022 - Inducing Positive Perspectives with Text Reframing Introduces Positive Psychology Frames Corpus Datasets * SDCNL: paper * Positive Psychology Frames corpus: website paper Workshops * ERISK: Early Risk Prediction on the Internet People * Diyi Yang Related Pages * Medical Domain NLP * NLP for Social Good text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:metaphor https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:metaphor&rev=1686814574&do=diff Metaphor and Figurative Language Overviews * Tong et al 2021 - Recent advances in neural metaphor processing: A linguistic, cognitive and social perspective Papers * Metaphor Detection * See FigLang * Metaphor Generation * Stowe et al 2021 - Exploring Metaphoric Paraphrase Generation * Metaphor Paraphrase * Search ACL Anthology - metaphor paraphrase * Mao et al 2018 - Word Embedding and WordNet Based Metaphor Identification and Interpretation * Bizzoni & Lappin 2018 … text/html 2024-09-18T18:01:06+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:modality https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:modality&rev=1726682466&do=diff Modality Papers * Vigus et al 2019 - A Dependency Structure Annotation for Modality Epistemic Modality (also known as factivity) * Saurí & Pustejovsky 2009 - FactBank: a corpus annotated with event factuality * Levels of possibility: improbable, slightly possible, possible, fairly possible, probable, very probable, most probably, most certainly, certainly (see page 12) * Sauri 2009 - FactBank 1.0 Annotation Guidelines * text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:morphological_analysis https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:morphological_analysis&rev=1686814574&do=diff Morphological Analysis Overviews * Morphological analysis with FSTs: Speech and Language Processing 2nd Ed, Ch 3 * Lecture: NLP 201 - Fall 2020 Oct 15 * Related work of Chahuneau 2013 (section 6) gives a very quick overview Unsupervised Analysers * Goldwater et al 2005 - Interpolating Between Types and Tokens by Estimating Power-Law Generators “We show that taking a particular stochastic process – the Pitman-Yor process – as an adaptor justifies the appearance of type frequencies in … text/html 2024-06-19T15:43:15+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:multilinguality https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:multilinguality&rev=1718811795&do=diff Multilinguality * Hu et al 2020 - XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization * Yu et al 2022 - Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources Datasets * Multilingual Dataset Survey People * Orhan Firat * Graham Neubig Related Pages * Cross-Lingual Transfer * Machine Translation text/html 2024-07-12T18:53:13+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:named_entity_recognition https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:named_entity_recognition&rev=1720810393&do=diff Named Entity Recognition General NER Papers * Lample et al 2016 - Neural Architectures for Named Entity Recognition * Yamada et al 2020 - LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention Sota on CoNLL-2003 * Reiss et al 2020 - Identifying Incorrect Labels in the CoNLL-2003 Corpus Corrected Dataset Low-Resource NER * Cotterell & Duh 2017 - Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields * Kej… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:narrative_understanding https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:narrative_understanding&rev=1686814574&do=diff Narrative Understanding Overviews * Piper et al 2021 - Narrative Theory for Computational Narrative Understanding * Finlayson 2013 - A Survey of Corpora in Computational and Cognitive Narrative Science Papers * Brahman et al 2021 - “Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding Datasets * Finlayson 2013 - A Survey of Corpora in Computational and Cognitive Narrative Science * LiSCU: paper A dataset of literary pieces, their summari… text/html 2025-02-04T18:08:23+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:natural_language_interfaces_to_databases https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:natural_language_interfaces_to_databases&rev=1738692503&do=diff Natural Language Interfaces to Databases Overviews * Articles * Historical * Androutsopoulos et al 1996 - Natural Language Interfaces to Databases – An Introduction * Books * Li et al 2023 - Natural Language Interfaces to Databases amazon Papers * Historical * Popescu et al 2003 - Towards a Theory of Natural Language Interfaces to Databases People * Yunyao Li Related Pages * Knowledge Graphs text/html 2024-06-19T22:15:05+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:negation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:negation&rev=1718835305&do=diff Negation Papers * Fancellu et al 2017 - Universal Dependencies to Logical Forms with Negation Scope * Fancellu et al 2017 - Detecting negation scope is easy, except when it isn’t Related Pages * Logic in NLP * Quantifiers * Semantics text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:negative_results https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:negative_results&rev=1686814574&do=diff Negative Results For examples of negative results in published papers, see a list here: Insightful paper examples * Workshop on Insights from Negative Results 2020 2021 text/html 2025-08-30T00:35:23+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:neurosymbolic_methods https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:neurosymbolic_methods&rev=1756514123&do=diff Neurosymbolic Methods Overviews * See related work (section 2) of Wu 2020 * d'Avila Garcez & Lamb 2020 - Neurosymbolic AI: The 3rd Wave * Zhang et al 2020 - Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs * Sheth et al 2023 - Neurosymbolic AI - Why, What, and How * Colelough & Regli 2025 - Neuro-Symbolic AI in 2024: A Systematic Review * Tutorials * NS4NLP: Neuro-Symbolic Modeling for NLP - COLING 2022 Tutorial Papers * Neural Module Networks * Murray … text/html 2025-01-17T21:22:27+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_for_environmental_issues https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_for_environmental_issues&rev=1737148947&do=diff NLP for Environmental Issues Papers * Wu 2019 - Application of Natural Language Processing in Environmental Protection Industry Based on Monte Carlo Tree Applies NLP to extract the data in environmental impact assessment documents (unstructured text), which is time-consuming and resource-intensive work. * Sarkar et al 2020 - Social Media Attributions in the Context of Water Crisis * Friederich et al 2021 - Automated Identification of Climate Risk Disclosures in Annual Corporate Reports … text/html 2024-10-25T03:18:57+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_for_math https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_for_math&rev=1729826337&do=diff NLP for Mathematics Overviews * Lu et al 2022 - A Survey of Deep Learning for Mathematical Reasoning Papers * Sachan et al 2017 - From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems * Petersen et al 2023 - Neural Machine Translation for Mathematical Formulae * Das et al 2024 - MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning Great paper. Has a nice overview of existing datasets * Gao et al… text/html 2025-05-31T07:43:17+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_for_social_good https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_for_social_good&rev=1748677397&do=diff NLP for Social Good Related to, and sometimes called, socially aware NLP. Overviews * Fortuna et al 2021 - Cartography of Natural Language Processing for Social Good: Definitions, Statistics and White Spots * Shi et al 2020 - Articial Intelligence for Social Good: A Survey * Hovy & Yang 2021 - The Importance of Modeling Social Factors of Language: Theory and Practice * Karamolegkou et al 2025 - NLP for Social Good: A Survey of Challenges, Opportunities, and Responsible Deployment Pa… text/html 2025-05-28T05:52:11+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_in_education https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_in_education&rev=1748411531&do=diff NLP in Education Papers * Ahmad et al 2007- Towards Automatic Conceptual Personalization Tools * Nielsen et al 2009 - Recognizing Entailment in Intelligent Tutoring Systems * CPS skills: 2019 - Towards a Generalized Competency Model of Collaborative Problem Solving * Pugh et al 2021 - Say What? Automatic Modeling of Collaborative Problem Solving Skills from Student Speech in the Wild * Suresh et al 2022 - The TalkMoves Dataset: K-12 Mathematics Lesson Transcripts Annotated for Teache… text/html 2025-03-20T03:56:09+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_meta_research https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_meta_research&rev=1742442969&do=diff NLP Meta Research Research and papers about NLP research. Papers * Michael et al 2022 - What Do NLP Researchers Believe? Results of the NLP Community Metasurvey * Kann et al 2022 - A Major Obstacle for NLP Research: Let’s Talk about Time Allocation! text/html 2026-03-05T00:18:45+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_outline https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_outline&rev=1772669925&do=diff Outline of NLP See also Outline of ML Key Papers in NLP NLP Tasks * Applications * AI Agents * AGI * Argumentative Text Understanding * Authorship Attribution * Automatic Essay Grading * Automatic Fact Checking * Automatic Grammar Checking, see Grammatical Error Correction * Autonomous Language Agents * Autonomous Scientific Research * Chatbots * ChatGPT * Commonsense Reasoning * Conversational Search * Data-to-Text * Debate, see Dialog - Debati… text/html 2026-03-05T00:19:08+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:nlp_tools https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:nlp_tools&rev=1772669948&do=diff NLP Tools * Gemini CLI text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:noisy_channel_model https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:noisy_channel_model&rev=1686814574&do=diff Noisy Channel Model Papers * Yu et al 2016 - The Neural Noisy Channel * Yee et al 2019 - Simple and Effective Noisy Channel Modeling for Neural Machine Translation “noisy channel models can outperform a direct model by up to 3.2 BLEU” * Jean & Cho 2020 - Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation * Yu et al 2020 - Better Document-Level Machine Translation with Bayes’ Rule Related Pages * Machine Translation * Statistical Mach… text/html 2024-05-03T03:37:02+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:non-autoregressive_seq2seq https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:non-autoregressive_seq2seq&rev=1714707422&do=diff Non-Autoregressive Sequence-to-Sequence Models Non-autoregressive seq2seq models produce outputs in parallel rather than one word at a time. Autoregressive vs Non-Autoregressive Definition: Autoregressive (Gu 2017): An autoregressive model generates tokens conditioned on the sequence of tokens previously generated. In other words, it operates one step at a time: it generates each token conditioned on the sequence of tokens previously generated. Examples of autoregressive models include RNNs… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:non-human_language_processing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:non-human_language_processing&rev=1686814574&do=diff Non-Human Language Processing NLP for non-human language, such as bird songs or animal calls. Papers * Bird songs * Tsai & Xue 2014 - On the Use of Speech Recognition Techniques to Identify Bird Species * Morfi et al 2019 - NIPS4Bplus: a richly annotated birdsong audio dataset * Morfi 2019 - Automatic detection and classification of bird sounds in low-resource wildlife audio datasets PhD thesis * Kahl et al 2021 - BirdNET: A deep learning solution for avian diversity monitoring … text/html 2024-06-19T21:55:24+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:offensive_language_detection https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:offensive_language_detection&rev=1718834124&do=diff Offensive Language Detection Toxic Language Detection / Hate Speech Detection * Zhou et al 2021 - Challenges in Automated Debiasing for Toxic Language Detection * Lee et al 2024 - Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis Datasets * Recent SemEval datasets * Jigsaw: Jigsaw Toxic Comment Classification Dataset People * Sandra Kübler text/html 2025-01-17T20:41:35+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:ontology_learning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:ontology_learning&rev=1737146495&do=diff Ontology Learning Papers * With LLMs * Lo et al 2024 - End-to-End Ontology Learning with Large Language Models Related Pages * Information Extraction * Knowledge Graphs text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:open_problems https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:open_problems&rev=1686814574&do=diff Open Problems Partial list of open problems in NLP. Explainability * Explainability is an open problem in machine learning and NLP. See Explainability. Machine Translation * Koehn & Knowles 2017 - Six Challenges for Neural Machine Translation Transformers * Transformers are hard to train (Liu et al 2020 - Understanding the Difficulty of Training Transformers), and often we can't even get them to overfit and just train a long as we can. This isn't a good situation, and shows there … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:papers https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:papers&rev=1686814574&do=diff <sortable> Year Title Notes 2002 Discriminative Training Methods for Hidden Markov Models - Theory and Experiments with Perceptron Algorithms Structured Perceptron 2018 Language Models are Unsupervised Multitask Learners GPT-2 2020 Language Models are Few-Shot Learners GPT-3 </sortable> text/html 2025-05-31T18:40:39+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:paper_examples https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:paper_examples&rev=1748716839&do=diff Examples of Good Papers This is a list of some good (well-written) papers in NLP. * Introduction of a new method * Bahdanau et al 2014 - Neural Machine Translation by Jointly Learning to Align and Translate * Hu et al 2022 - In-Context Learning for Few-Shot Dialogue State Tracking * Systematic exploration papers * Qi et al 2018 - When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation? Not-So-Good Examples Here are some papers that perhaps could have… text/html 2023-07-26T20:22:57+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:paraphrase https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:paraphrase&rev=1690402977&do=diff Paraphrase A common linguistic definition of paraphrase is that two sentences are paraphrases of each other if they mutually entail each other. Paraphrase Identification * Wieting & Gimpel 2017 - ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations Datasets * Microsoft Research Paraphrase Corpus: Dataset, paper: Dolan & Brockett 2003 - Automatically Constructing a Corpus of Sentential Paraphrases * PAWS: text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:patent_domain_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:patent_domain_nlp&rev=1686814574&do=diff Patent Domain NLP NLP in the patent domain. Overlaps with Legal Domain NLP and Scientific Text Processing. Papers * Classification * D'hondt et al 2013 - Text Representations for Patent Classification * Hepburn 2018 - Universal Language Model Fine-tuning for Patent Classification * Niu & Cai 2019 - A Label Informative Wide & Deep Classifier for Patents and Papers * Translation * 2005 Workshop on Patent Translation * Nanba et al 2012 - Automatic Translation of Scholarly Ter… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:perplexity https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:perplexity&rev=1686814574&do=diff Perplexity Perplexity can be used to evaluate the performance of language models. Conversion from log Probability to Perplexity To convert from loss (-log probability, aka cross entropy) to perplexity exponentiate the loss (perplexity = exp(loss)), and vice-versa (loss = ln(perplexity)). When the loss is very low (< .1) then the perplexity is roughly 1 + loss. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:planning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:planning&rev=1686814574&do=diff Planning Papers Search ACL Anthology for planning. * 2018 - Planning, Inference and Pragmatics in Sequential Language Games * 2020 - Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions * Huang et al 2022 - Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents * Valmeekam et al 2022 - Large Language Models Still Can't Plan (A Benchmark for LLMs on Planning and Reasoning about Change) * 2022 … text/html 2023-07-06T18:26:11+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:poem_generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:poem_generation&rev=1688667971&do=diff Poem Generation Papers * Jiang & Zhou 2008 - Generating Chinese Couplets using a Statistical MT Approach * Greene et al 2010 - Automatic analysis of rhythmic poetry with applications to generation and translation. * He et al Generating Chinese Classical Poems with Statistical Machine Translation Models * Colton et al 2012 - Full-FACE Poetry Generation Good references to pre-2012 work * Zhang & Lapata 2014 - Chinese Poetry Generation with Recurrent Neural Networks * Belouadi & Eger… text/html 2025-10-07T06:24:16+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:post-training https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:post-training&rev=1759818256&do=diff Post-Training Post-training refers to the things done to a LLM after pre-training to improve its performance, such as supervised fine-tuning, RLHF, instruction tuning, etc. This is a critical step before releasing the LLM. Typically, this refers to things done by the company or group before releasing the LLM, not the things done afterwards to customize to a specific application. (For an example of this usage, see the text/html 2023-07-07T18:11:34+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:pos_tagging https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:pos_tagging&rev=1688753494&do=diff Part-of-Speech Tagging Overviews * Speech and Language Processing 3rd Ch 8 - Sequence Labeling for Parts of Speech and Named Entities Papers For recent papers, see NLP Progress - POS Tagging. * DeRose 1988 - Grammatical Category Disambiguation by Statistical Optimization 1990 Thesis * Church 1988 - A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text One of the first statistical POS taggers, one of the papers that started the statistical/machine learning revolution … text/html 2026-02-20T06:35:45+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:pretraining https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:pretraining&rev=1771569345&do=diff Pretraining Overviews See also Language Model - Overviews. * Liu et al 2020 - A Survey on Contextual Embeddings * Qiu et al 2020 - Pre-trained Models for Natural Language Processing: A Survey Nice tables of pretraining methods on page 9 and 10, see Taxonomy of Pretraining Methods below. * Zhao et al 2023 - A Survey of Large Language Models Key and Early Papers For a history, see section 2.4 of Qiu 2020 or the related work in the GPT-2 paper. * Collobert et al 2011 - Natural Languag… text/html 2025-03-27T00:32:52+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:probing_experiments https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:probing_experiments&rev=1743035572&do=diff Probing Experiments in NLP * Linzen et al 2016 - Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies * Adi et al 2016 - Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks Tasks * SentEval People * Ryan Cotterell Related Pages * Neural Network Psychology * Interpretation (BERTology) * Mechanistic Interpretability * Visualizing Neural Networks text/html 2026-02-13T00:31:35+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:prompting https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:prompting&rev=1770942695&do=diff Prompting and In-Context Learning Overviews * Liu et al 2021 - Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing * Dong et al 2022 - A Survey on In-context Learning * Qiao et al 2022 - Reasoning with Language Model Prompting: A Survey Very good * Sahoo et al 2024 - A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications Not that great * Tutorials, Courses, Slides and Guides * Guides * … text/html 2025-10-08T09:16:35+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:prompt_engineering https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:prompt_engineering&rev=1759914995&do=diff Prompt Engineering Introductions and Overviews * Guides * A Beginner's Guide to ChatGPT Prompt Engineering Good concise intro (Accessed March 2025) * The Prompt Engineering Cheat Sheet Great * Prompt Engineering Guide This one is pretty good * Google Cloud - Prompt engineering: overview and guide * Overview Papers * Leidinger et al 2023 - The language of prompting: What linguistic properties make a prompt successful? * Slides * Blogs: * Lil'log Prompt Engineering … text/html 2024-08-20T06:07:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:quantifiers https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:quantifiers&rev=1724134051&do=diff Quantification Papers See also ACL Anthology - Quantification. * Hobbs 1983 - An Improper Treatment of Quantification in Ordinary English * Herbelot & Vecchi 2016 - Many speakers, many worlds: Interannotator variations in the quantification of feature norms * Bunt et al 2018 - Towards an ISO Standard for the Annotation of Quantification * 2019 - Probing Natural Language Inference Models through Semantic Fragments * Pustejovsky et al 2019 - Modeling Quantification and Scope in Abstra… text/html 2025-05-13T19:46:45+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:question_answering https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:question_answering&rev=1747165605&do=diff Question Answering Overviews Best overview: Baradaran et al 2020 - A Survey on Machine Reading Comprehension Systems. * Gao et al 2018 - Neural Approaches to Conversational AI (contains a chapter on QA) * Baradaran et al 2020 - A Survey on Machine Reading Comprehension Systems * Thayaparan et al 2020 - A Survey on Explainability in Machine Reading Comprehension * Rogers et al 2022 - QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension ACM … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:question_answering_papers https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:question_answering_papers&rev=1686814574&do=diff Question Answering: Papers Main page: Question Answering TODO: put in published ACL papers (main conferences, journals and workshops), as well as published ICLR and ML conference papers. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:question_generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:question_generation&rev=1686814574&do=diff Question Generation See Question Answering - Synthetic Question Generation. Overviews * Kurdi et al 2020 - A Systematic Review of Automatic Question Generation for Educational Purposes Papers * Mitkov & Ha 2003 - Computer-Aided Generation of Multiple-Choice Tests * Boyer & Piwek 2010 - Proceedings of QG2010: The Third Workshop on Question Generation pdf * Rus et al 2010 - The First Question Generation Shared Task Evaluation Challenge * Rus et al 2011 - Question Generation Shared T… text/html 2025-06-01T23:20:00+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:reasoning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:reasoning&rev=1748820000&do=diff Reasoning Definition of Reasoning * See definition in section 2 of Madabushi 2025 Reasoning Chains See also Chain of Thought Prompting. These papers use some sort of reasoning chain, including natural language reasons or natural language “rules.” * EntailmentBank: Dalvi et al 2021 - Explaining Answers with Entailment Trees Open domain, text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:recommender_systems https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:recommender_systems&rev=1686814574&do=diff Recommender Systems Related Pages * Learning to Rank text/html 2023-11-23T00:22:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:relation_extraction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:relation_extraction&rev=1700698951&do=diff Relation Extraction Overviews * Pawar et al 2017 - Relation Extraction : A Survey Very good survey * Smirnova & Cudre-Mauroux 2018 - Relation Extraction Using Distant Supervision: A Survey * Zhang et al 2020 - A Survey Deep Learning Based Relation Extraction Papers * Miwa & Bansal 2016 - End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures * Peng et al 2017 - Cross-Sentence N-ary Relation Extraction with Graph LSTMs * With LLMs * Wan et al 2023 - GPT-RE:… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:resources https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:resources&rev=1686814574&do=diff Resources * Finding the top papers in NLP in the last five years: Google Scholar CL * ACL * EMNLP * NAACL * TACL * COLING * EACL * CoNLL * WMT * CL * Misc resources: <https://sites.google.com/site/lyangwww/resources> text/html 2025-05-13T19:39:41+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:retrieval-augmented_methods https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:retrieval-augmented_methods&rev=1747165181&do=diff Retrieval-Augmented Methods (RAG) Overviews * Gao et al 2023 - Retrieval-Augmented Generation for Large Language Models: A Survey Papers * Lewis et al 2020 - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks * Liu et al 2021 - What Makes Good In-Context Examples for GPT-3? Cited by Rubin 2021 * Rubin et al 2021 - Learning To Retrieve Prompts for In-Context Learning Is this the first retrieval-based in-context learning paper? * Poesia et al 2022 - Synchromesh: Reliabl… text/html 2023-07-30T18:14:55+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:rnn https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:rnn&rev=1690740895&do=diff Recurrent Neural Networks RNN Variants * Zhang et al 2019 - A Lightweight Recurrent Network for Sequence Modeling Related to the Transformer, LRNs are a drop-in replacement to other RNNs, which remove the sequential natural of RNN processing. It essentially uses a Key-Query-Value attention mechanism instead of the recurrence. text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:robustness_in_nlp https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:robustness_in_nlp&rev=1686814574&do=diff Robustness and Brittleness in NLP (and Deep Learning) For an overview, read Jia 2017 and Jin 2019. Papers * Jia and Liang 2017 - Adversarial Examples for Evaluating Reading Comprehension Systems * Gururangan et al 2018 - Annotation Artifacts in Natural Language Inference Data * Poliak et al 2018 - Hypothesis Only Baselines in Natural Language Inference * Zellers et al 2018 - SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference Introduces Adversarial Filtering to … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:rule-based_systems https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:rule-based_systems&rev=1686814574&do=diff Rule-Based Systems Papers * Information Extraction * See Chapter 2 of Sarawagi 2008 - Information Extraction * Chiticariu et al 2013 - Rule-based Information Extraction is Dead! Long Live Rule-based Information Extraction Systems! * Topaz et al 2019 - Mining fall-related information in clinical notes: Comparison of rule-basedand novel word embedding-based machine learning approaches * Machine Translation * Boguslavsky 1995 - A Bi-directional Russian-to-English Machine Translat… text/html 2025-06-01T21:02:00+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:scientific_text_processing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:scientific_text_processing&rev=1748811720&do=diff Scientific Text Processing Overviews * Nasar et al 2018 - Information Extraction From Scientific Articles: A Survey Papers * 2013 - Purpose and Polarity of Citation: Towards NLP-based Bibliometrics * 2018 - Goal-Oriented Representation of Scientific Papers * Predicting Co-authors * Graph Structure * Vedak 2022 - ArXiv Citation Graph * Citation Processing * 2012 - Reference Scope Identification in Citing Sentences * Knowledge Base Construction * Hope et al 2021 - Extr… text/html 2025-04-01T21:50:52+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semantics https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semantics&rev=1743544252&do=diff Semantics Datasets List of datasets: * Corpora for English Semantics Related Pages * Abstract Meaning Representation AMR does a good job at capturing relational semantics (“who-is-doing-what-to-whom”), but is largly missing cross-sentence discourse structure, temporal information, causality, epistemic modality (factivity - whether an event happend or not), and quantifier scoping text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semantic_dependencies https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semantic_dependencies&rev=1686814574&do=diff Semantic Dependencies Parsing * SemEval 2014 Task 8 Papers * Oepen et al 2014 - SemEval 2014 Task 8: Broad-Coverage Semantic Dependency Parsing * Martins & Almeida 2014 - Priberam: A Turbo Semantic Parser with Second Order Features * SemEval 2015 Task 18 Papers * Oepen et al 2015 - SemEval 2015 Task 18: Broad-Coverage Semantic Dependency Parsing * Almeida & Martins 2015 - Lisbon: Evaluating TurboSemanticParser on Multiple Languages and Out-of-Domain Data (Non-neural) Was near … text/html 2025-01-17T20:38:43+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semantic_parsing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semantic_parsing&rev=1737146323&do=diff Semantic Parsing Overviews * Kamath & Das 2019 - A Survey on Semantic Parsing Semantic Role Labeling * Gildea & Jurafsky 2000 - Automatic Labeling of Semantic Roles Introduced broad-coverage semantic role labeling (SRL) * Gildea & Jurafsky 2002 - Automatic Labeling of Semantic Roles Longer journal article * PropBank * Strubell et al 2018 - Linguistically-Informed Self-Attention for Semantic Role Labeling (EMNLP 2018 Best Paper) Implicit Roles Related: Multi-sentence AMR. Implic… text/html 2025-03-20T01:48:05+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semantic_representations https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semantic_representations&rev=1742435285&do=diff Semantic Representations Overviews * S&LP Appendix F - Logical Representations of Sentence Meaning * Sadeddine et al 2024 - A Survey of Meaning Representations – From Theory to Practical Utility Representations Abstract Meaning Representation (AMR) See Abstract Meaning Representation. Combinatory Categorial Grammar (CCG) * Overviews * Steedman 1996 - A Very Short Introduction to CCG * ACL Wiki - Combinatory Categorial Grammar * Combinatory Categorial Grammar * Wikipedia … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semeval https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semeval&rev=1686814574&do=diff SemEval Timeline: SemEval data is usually available in the Fall and evaluation is in the month of January. By Year * 2022 tasks * 2021 tasks * 2020 tasks * 2019 tasks * 2018 tasks * 2017 tasks * 2016 tasks * 2015 tasks * 2014 tasks * 2013 tasks * 2012 tasks (SemEval-3) * 2010 (SemEval-2) * 2007 (SemEval-1) text/html 2023-07-03T18:59:28+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:semiring https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:semiring&rev=1688410768&do=diff Semiring Recent Papers * Opedal et al 2023 - Efficient Semiring-Weighted Earley Parsing (ACL 2023) Related Pages * Constituency Parsing text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:sentence_embeddings https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:sentence_embeddings&rev=1686814574&do=diff Sentence Embeddings Pre-trained Sentence Embeddings * SkipThought * FastSent * InferSent: Conneau et al 2017 - Supervised Learning of Universal Sentence Representations from Natural Language Inference Data * Reimers & Gurevych et al 2019 - Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Trained on NLI data (SNLI and Multi-Genre NLI datasets) * SimCSE: Gao et al 2021 - SimCSE: Simple Contrastive Learning of Sentence Embeddings Software * Sentence Transformers (PyTor… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:sentiment_analysis https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:sentiment_analysis&rev=1686814574&do=diff Sentiment Analysis Papers * Hutto & Gilbert 2013 - VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text This paper shocked everyone because it was SOTA at the time. It was a rule-based! text/html 2025-05-29T07:15:58+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:seq2seq https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:seq2seq&rev=1748502958&do=diff Sequence to Sequence Models Decoding Strategies See also Decoding. * Murray & Chiang 2018 - Correcting Length Bias in Neural Machine Translation * Nucleus Sampling: Holtzman et al 2019 - The Curious Case of Neural Text Degeneration * Wellek et al 2019 - Neural Text Generation with Unlikelihood Training * Stahlberg & Byrne 2019 - On NMT Search Errors and Model Errors: Cat Got Your Tongue? Exact decoding method for seq2seq models. Follow-up work: Shi et al 2020 - Why Neural Machine Tra… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:sequence_labeling https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:sequence_labeling&rev=1686814574&do=diff Sequence Labeling Semi-CRFs * Paper that introduced Semi-CRFs: Sarawagi & Cohen 2004 - Semi-Markov Conditional Random Fields for Information Extraction * Liu et al 2016 - Exploring Segment Representations for Neural Segmentation Models Shows that neural semi-CRF model benefit from representing the entire segment. Miscellaneous Models * Constrained Neural Model: Deutsch et al 2019 - A General-Purpose Algorithm for Constrained Sequential Inference text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:sign_language_processing https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:sign_language_processing&rev=1686814574&do=diff Sign Language Processing (SLP) Papers * Yin et al 2021 - Including Signed Languages in Natural Language Processing text/html 2023-11-22T22:19:24+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:software https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:software&rev=1700691564&do=diff Software General NLP: Parsing, NER, etc * Stanford Core NLP * <https://corenlp.run> * Stanza * Main site * Github * Tutorial: Stanza: A Tutorial on the Python CoreNLP Interface * Paper: Stanza: A Python Natural Language Processing Toolkit for Many Human Languages * NLTK * spaCy Annotation Tools * Prodigy (From the creators of spaCy) * brat rapid annotation tool github * doccano github Nilay has used this Scraping, etc * Web scraping * Beautiful Soup… text/html 2025-06-27T23:22:10+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:software_engineering https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:software_engineering&rev=1751066530&do=diff NLP for Software Engineering AI Tools * Cursor AI Code Editor * Gemini CLI Like Cursor, but open source. From Google Related Pages * Autonomous Language Agents text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:statistical_machine_translation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:statistical_machine_translation&rev=1686814574&do=diff Statistical Machine Translation Papers and software for statistical machine translation, mostly for historical refererence. See also Wikipedia - Statistical Machine Translation. Overviews * [Lopez 2008 - Statistical Machine Translation] or Lopez 2007 - A Survey of Statistical Machine Translation (older, but nicer formatting) IBM Models and Alignment * IBM Models * Brown et al 1988 - A Statistical Approach to Language Translation Overview paper of the approach text/html 2025-05-01T10:54:13+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:story_generation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:story_generation&rev=1746096853&do=diff Story Generation Papers * Martin et al 2017 - Event Representations for Automated Story Generation with Deep Neural Nets * Ammanabrolu et al 2019 - Story Realization: Expanding Plot Events into Sentences * Akoury et al 2020 - STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation github built upon this code Event Simulation See also Forecasting. * Li et al 2024 - Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play Datasets … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:structured_prediction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:structured_prediction&rev=1686814574&do=diff Structured Prediction Overviews * Jan 12 of NLP 202 (slides) and the readings for that lecture * Section 3.1-3.3 of Jeff's thesis gives an very brief overview of loss functions for structured prediction Key Papers * Structured Perceptron: Collins 2002 - Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms * Structured SVM text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:structured_prediction_energy_networks https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:structured_prediction_energy_networks&rev=1686814574&do=diff Structured Prediction Energy Networks (Also known as SPENs.) Summary (from Lyu - 2019): Papers * Belanger & McCallum 2015 - Structured Prediction Energy Networks * Belanger et al 2017 - End-to-End Learning for Structured Prediction Energy Networks * Rooshenas et al 2018 - Training Structured Prediction Energy Networks with Indirect Supervision * Rooshenas et al 2018 - Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks * Kevin Gimple's papers * … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:style_transfer https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:style_transfer&rev=1686814574&do=diff Style Transfer Overviews * Hu et al 2020 - Text Style Transfer: A Review and Experimental Evaluation * Jin et al 2020 - Deep Learning for Text Style Transfer: A Survey Papers * Fu 2017 - Style Transfer in Text: Exploration and Evaluation * Yang et al 2018 - Unsupervised Text Style Transfer using Language Models as Discriminators * Krishna et al 2020 - Reformulating Unsupervised Style Transfer as Paraphrase Generation website * Reif1 et al 2021 - A Recipe for Arbitrary Text Style … text/html 2025-05-14T18:33:38+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:summarization https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:summarization&rev=1747247618&do=diff Summarization Overviews Best overviews (as of 2021): [Klymenko & Braun 2020 - Automatic Text Summarization: A State-of-the-Art Review] and [El-Kassas et al 2021 - Automatic Text Summarization: A Comprehensive Survey] * General * Allahyari et al 2017 - Text Summarization Techniques: A Brief Survey * Nazari & Mahdavi 2019 - A survey on Automatic Text Summarization Kind of a weird survey * [Klymenko & Braun 2020 - Automatic Text Summarization: A State-of-the-Art Review] Good overview … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:supertasks https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:supertasks&rev=1686814574&do=diff Supertasks I believe Richard Socher may have introduced this terminology, see this tweet and these slides. Papers * Radford et al 2018 - Language Models are Unsupervised Multitask Learners * McCann et al 2018 - The Natural Language Decathlon: Multitask Learning as Question Answering (slides, talks about supertasks) Blogs, etc * Richard Socher's tweet regarding GPT-3: “There are 3 equivalent super tasks of NLP: Language models, dialogue systems and question answering. LMs have the most… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:syntax_in_deep_learning https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:syntax_in_deep_learning&rev=1686814574&do=diff Syntax in Deep Learning Papers * Strubell et al 2018 - Linguistically-Informed Self-Attention for Semantic Role Labeling (EMNLP 2018 Best paper) * 2019 - Joint Parsing and Generation for Abstractive Summarization * Zhang et al 2020 - SG-Net: Syntax Guided Transformer for Language Representation * Kumar et al 2020 - Syntax-guided Controlled Generation of Paraphrases * Zhu et al 2020 - The Return of Lexical Dependencies: Neural Lexicalized PCFGs text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:task_descriptions https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:task_descriptions&rev=1686814574&do=diff Natural Language Task Descriptions This page is about natural language task descriptions, which use natural language to describe tasks to be performed. This is similar to prompting, but the focus is on using the descriptions to generalize to new tasks, rather than focusing on improving performance on specific task(s). text/html 2023-09-08T18:39:18+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:task_oriented_dialog https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:task_oriented_dialog&rev=1694198358&do=diff Task Oriented Dialog Papers * Su et al 2021 - Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System Introduces PPTOD model * Discovering Latent Structure * Shi et al 2019 - Unsupervised Dialog Structure Learning * Zhang et al 2020 - A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning Few-Shot Task Oriented Dialog * Schema-Guided Dialog (SGD):2019 - Towards Scalable Multi-domain Conversational Agents: … text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:temporal_information_extraction https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:temporal_information_extraction&rev=1686814574&do=diff Temporal Information Extraction Overviews * Lim et al 2019 - Survey of Temporal Information Extraction Related Pages * Information Extraction * Time text/html 2025-03-22T02:55:35+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:test-time_scaling https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:test-time_scaling&rev=1742612135&do=diff Test-Time Scaling Test-time scaling refers to scaling up test-time compute to improve performance of a language model. While there are many methods of doing so, one such method is large reasoning models. Papers * Muennighof et al 2025 - s1: Simple Test-Time Scaling Related Pages * Large Reasoning Models text/html 2025-01-18T01:41:01+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:text-driven_forecasting https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:text-driven_forecasting&rev=1737164461&do=diff Text-Driven Forecasting See Smith 2010 - Text-Driven Forecasting. Examples See also Noah Smith's work on TDF * Predicting stock prices based on financial reports or news articles * Lee et al 2014 - On the Importance of Text Analysis for Stock Price Prediction * Predicting movie gross revenue based on reviews Related Pages * Forecasting text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:text_analytics https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:text_analytics&rev=1686814574&do=diff Text Analytics “Text analytics is the automated process of translating large volumes of unstructured text into quantitative data to uncover insights, trends, and patterns” (from MonkeyLearn.com). Related Pages * Text-Driven Forecasting * Topic Modeling text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:text_classification https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:text_classification&rev=1686814574&do=diff Text Classification Tutorials and Blog Posts * WARNING: Quality may vary * Binary and Multiclass Text Classification (auto detection in a model test pipeline) * Using Deep Learning for End to End Multiclass Text Classification * A Basic NLP Tutorial for News Multiclass Categorization Related Pages * Classification text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:text_simplification https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:text_simplification&rev=1686814574&do=diff Text Simplification Overviews See also NLP Progress - Simplification. * Alva-Manchego et al 2019 - Data-Driven Sentence Simplification: Survey and Benchmark Papers * Xu et al 2016 - Optimizing statistical machine translation for text simplification * Martin et al 2019 - Controllable Sentence Simplification Datasets and Evaluation * Alva-Manchego et al 2019 - EASSE: Easier automatic sentence simplification evaluation Collects a few text simplification datasets in one place * Shar… text/html 2023-11-17T21:16:55+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:time https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:time&rev=1700255815&do=diff Time and Temporal Information Temporal Parsing * Zhang & Xue 2018 - Structured Interpretation of Temporal Relations * Zhang & Xue 2018 - Neural Ranking Models for Temporal Dependency Structure Parsing * Ross et al 2020 - Exploring Contextualized Neural Language Models for Temporal Dependency Parsing * Yao et al 2023 - Textual Entailment for Temporal Dependency Graph Parsing Miscellaneous Papers * Lin et al 2020 - Conditional Generation of Temporally-ordered Event Sequences BART-bas… text/html 2024-07-12T03:28:42+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:tokenization https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:tokenization&rev=1720754922&do=diff Tokenization Tokenization is the process of splitting running text (which is a string of characters) into processing units, called tokens, which are usually either words or subword units. Tokenization usually has a large effect on the performance of a system. When testing methods, it's good to use a reasonable baseline such as BPE for tokenization, and to keep tokenization the same when comparing systems. It is common for improvements to tokenization to outweight possible model improvements.… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:topic_detection https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:topic_detection&rev=1686814574&do=diff Topic Detection Within a Discourse * 2003 - Semantic Language Models for Topic Detection and Tracking * Kim et al 2015 - Towards Improving Dialogue Topic Tracking Performances with Wikification of Concept Mentions * Zhang et al 2016 - Thread Cleaning and Merging for Microblog Topic Detection * 2019 - SECTOR: A Neural Model for Coherent Topic Segmentation and Classification Says “topic modeling (Blei et al., 2003) and TDT (Jin et al., 1999) focus on representing and extracting the seman… text/html 2023-09-06T09:33:05+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:topic_modeling https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:topic_modeling&rev=1693992785&do=diff Topic Modeling Topic modeling is used to analyze the distribution of words in documents. It assigns sets of words to “topics,” where each document contains one or more topics. Usually the topic assignments for words and documents is done using unsupervised methods, and doesn't correspond to a particular definition of topics. A popular method for topic modeling is Latent Dirichlet Allocation (LDA, text/html 2025-10-17T20:09:10+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:transformers https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:transformers&rev=1760731750&do=diff Transformers Overview * See Transformers in the ML Overview for introductory blog posts * Original paper: Vaswani et al 2017 - Attention Is All You Need * The Annotated Transformer * Textbook (SLP): Ch 9.7: Transformers * A walkthrough of transformer architecture code Contains a very good picture of the computation graph. Surveys * Lin et al 2021 - A Survey of Transformers Transformer Properties Time and Space Complexity: text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:unsupervised_methods https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:unsupervised_methods&rev=1686814574&do=diff Unsupervised Methods General Methods * EM algorithm * Density estimation, direct maximization of p(x) * Smith & Eisner 2006 - Contrastive Estimation: Training Log-Linear Models on Unlabeled Data Syntactic Parsing See also unsupervised constituency parsing and unsupervised dependency parsing. Overviews * Good historical overview: Nishida 2020 (Gives a good history of unsupervised parsing in the related work) * text/html 2025-07-03T04:05:39+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:vision_and_language https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:vision_and_language&rev=1751515539&do=diff Vision and Language This page is about vision and language tasks that are distinct from visual question answering (which only deals with question answering) or grounded language learning (which includes a learning component to the task). Overviews * Uppal et al 2020 - Multimodal Research in Vision and Language: A Review of Current and Emerging Trends * Multimodal Large Language Models (MLLMs) text/html 2023-08-30T23:33:24+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:visual_question_answering https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:visual_question_answering&rev=1693438404&do=diff Visual Question Answering Papers * Chen et al 2022 - MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text * Neural Module Networks * Andreas et al 2017 - Neural Module Networks * Hu et al 2017 - Learning to Reason: End-to-End Module Networks for Visual Question Answering Datasets * Visual QA: <https://visualqa.org/> People * Jacob Andreas * Dhruv Batra Related Pages * Grounded Language Learning * Image Captioning * Questi… text/html 2023-11-29T05:21:20+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:watermarking https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:watermarking&rev=1701235280&do=diff Watermarking Papers * Chen et al 2023 - X-Mark: Towards Lossless Watermarking Through Lexical Redundancy Has a nice introduction to the topic Related Pages * Generation text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:weighted_logic_programming https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:weighted_logic_programming&rev=1686814574&do=diff Weighted Logic Programming Overviews Papers * Lopez 2009 - Translation as Weighted Deduction * Mörbitz & Vogler 2019 - Weighted parsing for grammar-based language models (slides) See their related work * Balkır et al 2020 - Tensors over Semirings for Latent-Variable Weighted Logic Programs Neural Papers * Software * Dyna * Repository * Old repository: <https://github.com/nwf/dyna> * New repository: <https://github.com/matthewfl/dyna-R/> * Papers * Eisner et a… text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:wfsa https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:wfsa&rev=1686814574&do=diff Weighted FSAs and FSTs Weighted FSAs are the weighted generalizations of FSAs and FSTs. Key Papers * Mohri et al 2001 - Weighted Finite-State Transducers in Speech Recognition * Eisner 2002 - Parameter Estimation for Probabilistic Finite-State Transducers More Papers * Dreyer et al 2008 - Latent-Variable Modeling of String Transductions with Finite-State Methods * Dreyer et al 2009 - Graphical Models over Multiple Strings Recent Developments * Rastogi et al 2016 - Weighting Fini… text/html 2023-11-30T19:25:48+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:word-sense_disambiguation https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:word-sense_disambiguation&rev=1701372348&do=diff Word-Sense Disambiguation Papers * Scarlini et al 2019 - Just “OneSeC” for Producing Multilingual Sense-Annotated Data Datasets * OneSeC dataset People * Roberto Navigli text/html 2023-06-15T07:36:14+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:word_embeddings https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:word_embeddings&rev=1686814574&do=diff Word Embeddings Papers * Goldberg & Levy 2014 - word2vec Explained: Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method * Pennington et al 2014 - GloVe: Global Vectors for Word Representation Resources * GloVe Embeddings github For non-contextualized (fixed) word embeddings, GloVe is usually the best Related Pages * Pretraining text/html 2025-06-14T00:20:17+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:world_model https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:world_model&rev=1749860417&do=diff World Model Papers and Systems * V-Jepa 2 (from Meta) * Also one from Google Related Pages * Vision and Language text/html 2025-05-09T06:24:31+00:00 Anonymous (anonymous@undisclosed.example.com) nlp:writing_assistants https://jlab.soe.ucsc.edu/nlp-wiki/doku.php?id=nlp:writing_assistants&rev=1746771871&do=diff Writing Process / Writing Assistants Papers * Writing Assistants * Padmakumar & He 2023 - Does Writing with Language Models Reduce Content Diversity? * Writing Process * Wang et al 2025 - ScholaWrite: A Dataset of End-to-End Scholarly Writing Process Related Pages