NLP Wiki

User Tools

Site Tools

Trace: • image_captioning • text_analytics • relation_extraction • model_editing_and_unlearning • named_entity_recognition • autoencoders • meta-learning • topic_modeling • mixture_of_expert_models • graphical_models
nlp:structured_prediction

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:structured_prediction [2021/04/01 09:36] – jmflanignlp:structured_prediction [2023/06/15 07:36] (current) – external edit 127.0.0.1
Line 11: Line 11:
 ===== Recent Papers ===== ===== Recent Papers =====
 Recent papers: [[https://paperswithcode.com/task/structured-prediction]] Recent papers: [[https://paperswithcode.com/task/structured-prediction]]
-  * [[https://arxiv.org/pdf/1603.06042.pdf|Andor et al 2016 - Globally Normalized Transition-Based Neural Networks]]  Talks about the label bias problem.+  * [[https://arxiv.org/pdf/1603.06042.pdf|Andor et al 2016 - Globally Normalized Transition-Based Neural Networks]]  Talks about the [[label bias problem]].
   * [[https://arxiv.org/pdf/1711.04956v5.pdf|Edunov et al 2017 - Classical Structured Prediction Losses for Sequence to Sequence Learning]]  Uses a sample (i.e. beam) size of 16 for the MT experiments.  See section 6.5 and Table 2.   * [[https://arxiv.org/pdf/1711.04956v5.pdf|Edunov et al 2017 - Classical Structured Prediction Losses for Sequence to Sequence Learning]]  Uses a sample (i.e. beam) size of 16 for the MT experiments.  See section 6.5 and Table 2.
   *  [[https://arxiv.org/pdf/1807.01745.pdf|Gómez-Rodríguez et al 2018 - Global Transition-based Non-projective Dependency Parsing]]   *  [[https://arxiv.org/pdf/1807.01745.pdf|Gómez-Rodríguez et al 2018 - Global Transition-based Non-projective Dependency Parsing]]
 +  * [[https://www.aclweb.org/anthology/P18-1173.pdf|Peng et al 2018 - Backpropagating through Structured Argmax using a SPIGOT]] (see also [[ml:Optimization in Deep Learning#Backpropagating Through Discontinuities]])
   * [[https://arxiv.org/pdf/1906.07880.pdf|Wang et al 2018 - Second-Order Semantic Dependency Parsing with End-to-End Neural Networks]]   * [[https://arxiv.org/pdf/1906.07880.pdf|Wang et al 2018 - Second-Order Semantic Dependency Parsing with End-to-End Neural Networks]]
 +  * [[https://www.aclweb.org/anthology/K18-1001.pdf|Thai et al 2018 - Embedded-State Latent Conditional Random Fields for Sequence Labeling]]
   * [[https://par.nsf.gov/servlets/purl/10145797|Ma et al 2019 - Randomized Greedy Search for Structured Prediction: Amortized Inference and Learning]]   * [[https://par.nsf.gov/servlets/purl/10145797|Ma et al 2019 - Randomized Greedy Search for Structured Prediction: Amortized Inference and Learning]]
   * **[[http://proceedings.mlr.press/v97/collobert19a/collobert19a.pdf|Collobert 2019 - A Fully Differentiable Beam Search Decoder]]**   * **[[http://proceedings.mlr.press/v97/collobert19a/collobert19a.pdf|Collobert 2019 - A Fully Differentiable Beam Search Decoder]]**
 +  * [[https://www.aclweb.org/anthology/N19-1171.pdf|Goyal et al 2019 - An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search]]
 +  * [[https://www.aclweb.org/anthology/N19-1335.pdf|Tu & Gimple 2019 - Benchmarking Approximate Inference Methods for Neural Structured Prediction]]
   * [[https://www.aclweb.org/anthology/D19-1099.pdf|2019 - Semantic Role Labeling with Iterative Structure Refinement]] Good related work section   * [[https://www.aclweb.org/anthology/D19-1099.pdf|2019 - Semantic Role Labeling with Iterative Structure Refinement]] Good related work section
   * [[https://arxiv.org/pdf/2005.00975.pdf|Zhang et al 2020 - Efficient Second-Order TreeCRF for Neural Dependency Parsing]]   * [[https://arxiv.org/pdf/2005.00975.pdf|Zhang et al 2020 - Efficient Second-Order TreeCRF for Neural Dependency Parsing]]
Line 23: Line 27:
   * [[https://www.aclweb.org/anthology/2020.acl-main.776.pdf|Fonseca & Martins 2020 - Revisiting Higher-Order Dependency Parsers]]   * [[https://www.aclweb.org/anthology/2020.acl-main.776.pdf|Fonseca & Martins 2020 - Revisiting Higher-Order Dependency Parsers]]
   * [[https://arxiv.org/pdf/2101.10435.pdf|Widmoser 2021 - Randomized Deep Structured Prediction for Discourse-Level Processing]] "Our experiments show that in all cases, deep structured prediction outperforms traditional shallow approaches, structured learning outperforms inference over locally trained models, and generic randomized inference performs competitively to exact inference."   * [[https://arxiv.org/pdf/2101.10435.pdf|Widmoser 2021 - Randomized Deep Structured Prediction for Discourse-Level Processing]] "Our experiments show that in all cases, deep structured prediction outperforms traditional shallow approaches, structured learning outperforms inference over locally trained models, and generic randomized inference performs competitively to exact inference."
 +
 +==== Conferences and Workshops ====
 +  * [[https://www.aclweb.org/anthology/2020.spnlp-1.0.pdf|4th Workshop on Structured Prediction for NLP]]
 +
 +==== Courses and Tutorials ====
 +  * Structured Prediction for Language and Other Discrete Data (SPFLODD) course at CMU: [[http://demo.clab.cs.cmu.edu/fa2015-11763/|2015]] [[https://sites.google.com/site/spflodd/|2014]]
  
 ===== Related Pages ===== ===== Related Pages =====
   * [[Structured Prediction Energy Networks]]   * [[Structured Prediction Energy Networks]]
 +  * [[Label Bias Problem]]
nlp/structured_prediction.1617269774.txt.gz · Last modified: 2023/06/15 07:36 (external edit)
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki