====== Abstract Meaning Representation ======

==== Introductions and Overviews ====
  * **[[https://github.com/amrisi/amr-guidelines/blob/master/amr.md#part-i-introduction|Introduction]]** The best introduction to AMR.
  * [[https://amr.isi.edu/index.html|AMR website]]
  * [[https://aclanthology.org/W13-2322.pdf|Banarescu et al 2013 - Abstract Meaning Representation for Sembanking]]
  * [[AMR Annotation]]
    * [[https://www.isi.edu/~ulf/amr/lib/amr-dict.html|AMR Dict]] List of linguistic phenomena and how to handle them in AMR
  * [[https://nert-nlp.github.io/AMR-Bibliography/|AMR Bibliography]]
  * Generation
    * [[https://arxiv.org/pdf/2206.07328.pdf|Hao et al 2022 - A Survey : Neural Networks for AMR-to-Text]]
  * **Applications**
    * [[https://aclanthology.org/2024.emnlp-main.390.pdf|Wein & Opizt - A Survey of AMR Applications]]

===== Papers =====
See an updated list of AMR papers here: [[https://nert-nlp.github.io/AMR-Bibliography/|AMR Bibliography]]

==== Parsing ====
See also [[Semantic Parsing]] and [[https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=amr+parsing&btnG=|Google Scholar - AMR Parsing]].
  * Graph-based
    * [[https://jflanigan.github.io/flanigan+etal.acl2014.pdf|Flanigan et al 2014 - A Discriminative Graph-Based Parser for the Abstract Meaning Representation]]
    * [[https://arxiv.org/pdf/1805.05286.pdf|Lyu & Titov 2018 - AMR Parsing as Graph Prediction with Latent Alignment]]
    * [[https://aclanthology.org/2020.acl-main.397.pdf|Zhou et al 2020 - AMR Parsing with Latent Structural Information]]
    * [[https://aclanthology.org/2022.acl-long.415.pdf|Bai et al 2022 - Graph Pre-training for AMR Parsing and Generation]]
  * Transition-based
    * [[https://www.aclweb.org/anthology/N15-1040.pdf|Wang et al 2015 - A Transition-based Algorithm for AMR Parsing]]
    * [[https://arxiv.org/pdf/1702.05053.pdf|Peng et al 2017 - Addressing the Data Sparsity Issue in Neural AMR Parsing]]
    * [[https://arxiv.org/pdf/1707.07755.pdf|Ballesteros & Al-Onaizan 2017 - AMR Parsing using Stack-LSTMs]]
    * [[https://aclanthology.org/P19-1451.pdf|Naseem et al 2019 - Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning]]
    * [[https://arxiv.org/pdf/2004.05572.pdf|Cai & Lam 2020 - AMR Parsing via Graph Sequence Iterative Inference]]  I would classify this approach as a transition-based algorithm that incrementally builds the graph
    * [[https://aclanthology.org/2020.findings-emnlp.89.pdf|Astudillo et al 2020 - Transition-based Parsing with Stack-Transformers]]
    * [[https://aclanthology.org/2021.naacl-main.443.pdf|Zhou et al 2021 - AMR Parsing with Action-Pointer Transformer]]
    * [[https://aclanthology.org/2022.naacl-main.80.pdf|Drozdov et al 2022 - Inducing and Using Alignments for Transition-based AMR Parsing]]
  * Grammar-based
    * [[https://www.aclweb.org/anthology/D15-1198.pdf|Artzi et al 2015 - Broad-coverage CCG Semantic Parsing with AMR]]
    * [[https://aclanthology.org/J19-2005.pdf|Gildea et al 2019 - Ordered Tree Decomposition for HRG Rule Extraction]]
  * Seq2seq
    * [[https://arxiv.org/pdf/1704.08381.pdf|Konstas et al 2017 - Neural AMR: Sequence-to-Sequence Models for Parsing and Generation]]
    * [[https://www.ijcai.org/proceedings/2019/0691.pdf|Ge et al 2019 - Modeling Source Syntax and Semantics for Neural AMR Parsing]]
    * [[https://www.aclweb.org/anthology/2020.emnlp-main.196.pdf|Xu et al 2020 - Improving AMR Parsing with Sequence-to-Sequence Pre-training]]
    * AMRBART: [[https://arxiv.org/pdf/2203.07836.pdf|Bai et al 2022 - Graph Pre-training for AMR Parsing and Generation]] (SOTA as of March 2023)
    * BiBL: [[https://aclanthology.org/2022.coling-1.485.pdf|Cheng et al 2023 - BiBL: AMR Parsing and Generation with Bidirectional Bayesian Learning]]
  * Prompted LLMs
    * [[https://arxiv.org/pdf/2304.12272.pdf|Lee et al 2023 - AMR Parsing with Instruction Fine-tuned Pre-trained Language Models]]
  * Other methods
    * [[https://aclanthology.org/D16-1065.pdf|Zhou et al 2016 - AMR Parsing with an Incremental Joint Model]] Has a joint model for concept and relation identification. Compares to the same feature set as JAMR.
    * [[https://aclanthology.org/D19-1393.pdf|Cai & Lam 2019 - Core Semantic First: A Top-down Approach for AMR Parsing]]
    * [[https://aclanthology.org/D19-1392.pdf|Zhang et al 2019 - Broad-Coverage Semantic Parsing as Transduction]]
    * [[https://aclanthology.org/2020.emnlp-main.323.pdf|Lindemann et al 2020 - Fast semantic parsing with well-typedness guarantees]]
  * Domain Adaptation
    * [[https://arxiv.org/pdf/2210.12445.pdf|Bai et al 2022 - Cross-domain Generalization for AMR Parsing]]

==== Generation =====
See also [[Generation]]
  * [[https://www.aclweb.org/anthology/2020.tacl-1.2.pdf|Wang et al 2020 - AMR-To-Text Generation with Graph Transformer]]
  * [[https://arxiv.org/pdf/2012.15793.pdf|Hoyle et al 2020 - Promoting Graph Awareness in Linearized Graph-to-Text Generation]]

==== Applications ====
  * Machine Translation
    * [[https://arxiv.org/pdf/1902.07282.pdf|Song et al 2019 - Semantic Neural Machine Translation using AMR]]
    * [[https://ieeexplore.ieee.org/iel7/9335828/9335829/09335896.pdf|Nguyen et al 2020 - Integrating AMR to Neural Machine Translation using Graph Attention Networks]]
    * [[https://downloads.hindawi.com/journals/mpe/2021/9939389.pdf|Nguyen et al 2021 - Improving Neural Machine Translation with AMR Semantic Graphs]]
    * [[https://aclanthology.org/2022.dlg4nlp-1.2.pdf|Li & Flanigan 2022 - Improving Neural Machine Translation with the Abstract Meaning Representation by Combining Graph and Sequence Transformers]]
    * [[https://arxiv.org/pdf/2304.11501|Wein & Schneider 2023 - Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation]]
  * Summarization
    * [[https://aclanthology.org/N15-1114.pdf|Liu et al 2015 - Toward Abstractive Summarization Using Semantic Representations]]
    * [[https://arxiv.org/pdf/1806.05655.pdf|Liao et al 2018 - Abstract Meaning Representation for Multi-Document Summarization]]
    * [[https://assets.researchsquare.com/files/rs-1938526/v1_covered.pdf?c=1664538289|Kouris et al 2022 - Text Summarization Based on Semantic Graphs: An Abstract Meaning Representation Graph-to-Text Deep Learning Approach]]
    * [[https://aclanthology.org/2022.naacl-main.236.pdf|Ribeiro et al 2022 - FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations]]
    * (See also [[https://scholar.google.com/citations?user=22ohn6AAAAAJ&hl=en|Fei Liu's Publications]])
    * [[https://arxiv.org/pdf/2311.09521|Qiu et al 2024 - AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation]]
  * Applications to (or with) LLMs
    * [[https://arxiv.org/pdf/2405.18414|Jiang et al 2024 - Don’t Forget to Connect! Improving RAG with Graph-based Reranking]]
  * Question Answering
    * [[http://www.public.asu.edu/~cbaral/papers/aaai2016-sub.pdf|Mitra & Baral 2016-  Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning]]
    * [[https://aclanthology.org/2020.coling-main.222.pdf|Lim et al 2020 - I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning]]
    * [[https://arxiv.org/pdf/2012.01707.pdf|Kapanipathi et al 2021 - Leveraging Abstract Meaning Representation for Knowledge Base Question Answering]]
    * [[https://arxiv.org/pdf/2109.02905.pdf|Xu et al 2021 - Exploiting Reasoning Chains for Multi-hop Science Question Answering]]
    * [[https://aclanthology.org/2021.findings-acl.90.pdf|Xu et al 2021 - Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering]]
    * [[https://arxiv.org/pdf/2206.08486.pdf|Deng et al 2022 - Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering]]
    * [[https://arxiv.org/pdf/2305.17050|Wang et al 2023 - Exploiting Abstract Meaning Representation for Open-Domain Question Answering]]
  * Classification
    * [[https://openreview.net/pdf?id=dhf_LF2WDQS|Ma et al 2023 - AMR-based Path Aggregation Graph Network for Aspect-based Sentiment Analysis]] At ACL 2023
  * Information Extraction
    * [[https://aclanthology.org/N15-1119.pdf|Pan et al 2015 - Unsupervised Entity Linking with Abstract Meaning Representation]]
    * [[https://arxiv.org/pdf/1512.01587.pdf|Garg et al 2015 - Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text]]
    * [[https://aclanthology.org/W17-2315.pdf|Rao et al 2017 - Biomedical Event Extraction using Abstract Meaning Representation]]
  * Dialog
    * [[https://www.aclweb.org/anthology/2020.lrec-1.86.pdf|Bonial et al 2020 - Dialogue-AMR: Abstract Meaning Representation for Dialogue]]
    * [[https://arxiv.org/pdf/2105.10188.pdf|Bai et al 2021 - Semantic Representation for Dialogue Modeling]]
  * Prompting and LLMs
    * [[https://arxiv.org/pdf/2405.01502|Jin et al 2024 - Analyzing the Role of Semantic Representations in the Era of Large Language Models]] Uses AMR in a CoT-style prompt
  * Fact-Checking
    * [[https://aclanthology.org/2022.naacl-main.236.pdf|Ribeiro et al 2022 - FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations]]
  * Style-Transfer
    * [[https://arxiv.org/pdf/2212.01667|Jangra et al 2022 - T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation]]
  * Data Augmentation
    * [[https://aclanthology.org/2022.findings-acl.244.pdf|Shou et al 2022 - AMR-DA: Data Augmentation by Abstract Meaning Representation]] Augments the data by parsing with AMR parser, manipulating the graph, and generating a new sentence.  They used it for textual similarity task.
  * Embodied or Vision and Language
    * [[https://aclanthology.org/2022.dlg4nlp-1.4.pdf|Choi et al 2022 - Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models]] Not really vision related. Uses AMR to help with caption to scene-graph parsing
  * Pre-training and Embedding Representations
    * [[https://arxiv.org/pdf/2206.07023.pdf|Opitz & Frank 2022 - SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features]]

==== AMR Extensions ====
  * Other languages than English
    * Chinese & Czech: [[http://www.lrec-conf.org/proceedings/lrec2014/pdf/384_Paper.pdf|Xue et al 2014 - Not an Interlingua, but Close: Comparison of English AMRs to Chinese and Czech]]
    * Chinese: [[https://aclweb.org/anthology/W/W16/W16-1702.pdf|Li et al 2016 - Annotating the Little Prince with Chinese AMRs]]
    * [[https://www.aclweb.org/anthology/2020.dmr-1.4.pdf|Vigus 2020 - Cross-Lingual Annotation: A Road Map for Low- and No-Resource Languages]]
  * [[Abstract Meaning Representation#Multi-sentence AMR]]
  * Time and Temporal Information
    * [[https://www.aclweb.org/anthology/W18-4912.pdf|Donatelli et al 2018 - Annotation of Tense and Aspect Semantics for Sentential AMR]]
  * [[https://www.aclweb.org/anthology/2020.dmr-1.2.pdf|Bos 2020 - Separating Argument Structure from Logical Structure in AMR]]
  * Quantifier Scoping and Inference
    * [[https://arxiv.org/pdf/2109.09858.pdf|Williamson et al 2021 - Intensionalizing Abstract Meaning Representations: Non-Veridicality and Scope]]
  * UMR
    * [[https://www.aclweb.org/anthology/W19-3303.pdf|Pustejovsky et al 2019 - Modeling Quantification and Scope in Abstract Meaning Representations]]
    * [[https://link.springer.com/article/10.1007/s13218-021-00722-w|Van Gysel et al 2021 - Designing a Uniform Meaning Representation for Natural Language Processing]] ([[https://link.springer.com/content/pdf/10.1007/s13218-021-00722-w.pdf|pdf]])
    * [[https://github.com/umr4nlp/umr-guidelines/blob/master/guidelines.md|UMR Guidelines]]
  * Interlingual extensions
    * BabelNet Meaning Representation (BMR): [[https://aclanthology.org/2022.acl-long.121.pdf|Lorenzo et al 2022 - Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation]]
  * [[https://www.aclweb.org/anthology/2020.lrec-1.601.pdf|Bonn et al 2020 - Spatial AMR: Expanded Spatial Annotation in the Context of a Grounded Minecraft Corpus]]
  * Dialog
    * [[https://www.aclweb.org/anthology/2020.lrec-1.86.pdf|Bonial et al 2020 - Dialogue-AMR: Abstract Meaning Representation for Dialogue]]
    * [[https://iwcs2021.github.io/proceedings/iwcs/pdf/2021.iwcs-1.17.pdf|Bonial et al 2021 - Builder, we have done it: Evaluating & Extending Dialogue-AMR NLU Pipeline for Two Collaborative Domains]]
  * [[https://www.aclweb.org/anthology/2020.dmr-1.1.pdf|Lai et al 2020 - A Continuation Semantics for Abstract Meaning Representation]]
  * [[http://www.lrec-conf.org/proceedings/lrec2022/workshops/LAWXVI/pdf/2022.lawxvi-1.19.pdf|Ji et al 2022 - Automatic Enrichment of Abstract Meaning Representations]]


==== Evaluation ====
  * Parsing
    * Fine-grained evaluation: [[https://arxiv.org/pdf/1608.06111|Damonte et al 2016 - An Incremental Parser for Abstract Meaning Representation]] (see section 5)
    * [[https://arxiv.org/pdf/1905.10726.pdf|Song & Gildea 2019 - SemBleu: A Robust Metric for AMR Parsing Evaluation]] ([[https://github.com/freesunshine0316/sembleu|github]])
    * [[https://arxiv.org/pdf/2210.06461|Opitz & Frank 2022 - Better Smatch = Better Parser? AMR evaluation is not so simple anymore]]
    * [[https://arxiv.org/pdf/2305.06993|Opitz 2023 - SMATCH++: Standardized and Extended Evaluation of Semantic Graphs]] [[https://github.com/flipz357/smatchpp|github]]
  * Generation
    * [[https://arxiv.org/pdf/2008.08896.pdf|Opitz & Frank 2020 - Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR]]

===== Software =====
  * Parsers
    * This one works well: [[https://arxiv.org/pdf/2004.05572.pdf|Cai & Lam 2020 - AMR Parsing via Graph Sequence Iterative Inference]] Rongwen has been using it. Ask him if you want help running it.
  * Libraries for reading AMR graphs
    * [[https://github.com/goodmami/penman|Penman — a Python library for PENMAN graph notation]] [[https://penman.readthedocs.io/en/latest/index.html|docs]]
  * Alignment
    * [[https://aclanthology.org/D14-1048.pdf|Pourdamghani et al 2015 - Aligning English Strings with Abstract Meaning Representation Graphs]] [[https://www.isi.edu/~damghani/papers/Aligner.zip|software]] or this [[https://amrlib.readthedocs.io/en/latest/isi_aligner/|software]] This is the aligner that was used to produce the alignments in the AMR LDC data.
    * [[https://aclanthology.org/N15-3008.pdf|Saphra & Lopez 2015 - AMRICA: an AMR Inspector for Cross-language Alignments]]

===== Multi-sentence AMR =====
Related: [[Coreference Resolution]], [[semantic_parsing#Implicit Roles]]
  * **[[https://www.aclweb.org/anthology/C18-1313.pdf|O’Gorman et al 2018 - AMR Beyond the Sentence: the Multi-sentence AMR corpus]]** (this data is released in AMR 3.0 [[https://catalog.ldc.upenn.edu/LDC2020T02|LDC2020T02]])
    * [[https://github.com/timjogorman/Multisentence-AMR-guidelines/blob/master/ms-amr.md|Multisentence AMR Guidelines]]
  * Related work: [[https://arxiv.org/pdf/1911.03766.pdf|Ebner et al 2019 - Multi-Sentence Argument Linking]]
  * [[https://www.aclweb.org/anthology/2020.crac-1.4.pdf|Anikina et al 2020 - Predicting Coreference in Abstract Meaning Representations]]
  * [[https://aclanthology.org/2021.acl-long.324.pdf|Fu et al 2021 - End-to-End AMR Coreference Resolution]] First paper to do document coreferenece for AMRs (not full multi-document AMRs because missing implicit roles). The input is AMR, doesn't actually use the text ([[https://github.com/Sean-Blank/AMRcoref|github]])
  * [[https://arxiv.org/pdf/2112.08513.pdf|Naseem et al 2022 - DOCAMR: Multi-Sentence AMR Representation and Evaluation]]

===== Guesture, Situated, and Visual AMRs =====
  * Annotation Schemes
    * [[https://aclanthology.org/2022.lrec-1.169.pdf|Brutti et al 2022 - Abstract Meaning Representation for Gesture]]
    * [[https://link.springer.com/chapter/10.1007/978-3-031-06018-2_21|Donatelli et al 2022 - Towards Situated AMR: Creating a Corpus of Gesture AMR]]
  * Parsers
    * [[https://aclanthology.org/2022.dlg4nlp-1.4.pdf|Choi et al 2022 - Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models]]
    * [[https://arxiv.org/pdf/2210.14862.pdf|Abdelsalam et al 2022 - Visual Semantic Parsing: From Images to Abstract Meaning Representation]]

===== Software and Resources =====
  * [[https://github.com/IBM/transition-amr-parser|IBM AMR Parser]]

===== People =====
  * [[https://scholar.google.com/citations?user=pxc_-XYAAAAJ&hl=en|Martha Palmer]]
  * [[https://scholar.google.com/citations?user=56UT_6IAAAAJ&hl=en|James Pustejovsky]]
  * [[https://scholar.google.com/citations?user=yWZdmLYAAAAJ&hl=en|Linfeng Song]]
  * [[https://scholar.google.com/citations?user=KlVbOkMAAAAJ&hl=en|Nianwen Xue]]

===== Related Pages =====
  * [[AMR Annotation]]
  * [[ml:graph_nn|Graph Neural Networks]]
  * [[Semantic Representations]]