====== Constituency Parsing ======

===== Supervised Constituency Parsing =====
See also [[http://nlpprogress.com/english/constituency_parsing.html|NLP Progress - Constituency parsing]]

=== CKY Parsing ===
  * General Papers
    * See also [[https://en.wikipedia.org/wiki/CYK_algorithm|Wikipedia - CYK algorithm]]
  * Semi-ring parsing, see also [[Semiring]]
    * Goodman 1999
  * Hypergraph parsing, see also [[Hypergraphs]]
    * [[https://www.aclweb.org/anthology/W01-1812.pdf|Klein & Manning 2001 - Parsing and Hypergraphs]]
    * [[https://www.aclweb.org/anthology/C08-5001.pdf|Huang 2008 - Advanced Dynamic Programming in Semiring and Hypergraph Frameworks]]
  * Extensions
    * Generalized CKY (CKY+).  Handles grammars not in CNF form (handles nplCF - non partially lexicalized CF grammars): [[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.18.811&rep=rep1&type=pdf|Chappelier & Rajman 1998 - A generalized CYK algorithm for parsing stochastic CFG]]
    * [[https://www.aclweb.org/anthology/W14-4011.pdf|Sennrich 2014 - A CYK+ Variant for SCFG Decoding Without a Dot Chart]] Improved CKY+ algorithm for SCFG parsing
  * Re-Ranking Parsers
    * [[https://aclanthology.org/P05-1022.pdf|Charniak & Johnson 2005 - Coarse-to-fine n-best parsing and MaxEnt discriminative reranking]]
    * [[https://aclanthology.org/N06-1020.pdf|McClosky et al 2006 - Effective Self-Training for Parsing]]
    * [[https://aclanthology.org/P08-1067.pdf|Huang et al 2008 - Forest Reranking: Discriminative Parsing with Non-Local Feature]] 91.7 on PTB. Was SOTA until [[https://aclanthology.org/P12-1046.pdf|Shindo 2012]]
    * [[https://aclanthology.org/D16-1257.pdf|Choe & Charniak 2016 - Parsing as Language Modeling]]
  * Parsers Using CKY
    * [[https://aclanthology.org/P14-1022.pdf|Hall et al 2014 - Less Grammar, More Features]]
  * Neural Parsers that use CKY
    * [[https://arxiv.org/pdf/1507.03641.pdf|Durrett & Klein 2015 - Neural CRF Parsing]]
    * [[https://arxiv.org/pdf/1705.03919.pdf|Stern et al 2017 - A Minimal Span-Based Neural Constituency Parser]]
    * [[https://arxiv.org/pdf/1804.07853.pdf|Gaddy et al 2018 - What's Going On in Neural Constituency Parsers? An Analysis]]
    * [[https://arxiv.org/pdf/1805.01052.pdf|Kitaev & Klein 2018 - Constituency Parsing with a Self-Attentive Encoder]]
    * [[https://arxiv.org/pdf/1911.03875.pdf|Mrini et al 2019 - Rethinking Self-Attention: Towards Interpretability in Neural Parsing]] Current SOTA (as of 2021)
    * [[https://arxiv.org/pdf/2008.03736.pdf|Zhang et al 2020 - Fast and Accurate Neural CRF Constituency Parsing]] ([[https://www.ijcai.org/Proceedings/2020/560/|talk]])

=== Other approaches ===
  * Transition-based, Shift-reduce, or Incremental Constituency Parsing
    * Non-Neural
      * [[https://aclanthology.org/P13-1043.pdf|Zhu et al 2013 - Fast and Accurate Shift-Reduce Constituent Parsing]]
    * Neural
      * [[https://aclanthology.org/P15-1113.pdf|Watanabe & Sumita 2015 - Transition-based Neural Constituent Parsing]]
      * [[https://arxiv.org/pdf/1612.00567.pdf|Liu & Zhang 2016 - Shift-Reduce Constituent Parsing with Neural Lookahead Features]]
      * [[https://aclanthology.org/Q17-1029.pdf|Liu & Zhang 2018 - In-Order Transition-based Constituent Parsing]]
      * [[https://aclanthology.org/Q19-1005.pdf|Coavoux et al 2019 - Unlexicalized Transition-based Discontinuous Constituency Parsing]]
      * [[https://proceedings.neurips.cc/paper/2020/file/f7177163c833dff4b38fc8d2872f1ec6-Paper.pdf|Yang & Deng 2020 - Strongly Incremental Constituency Parsing with Graph Neural Networks]]
  * Top-Down Parsing
    * [[https://arxiv.org/pdf/1705.03919.pdf|Stern et al 2017 - A Minimal Span-Based Neural Constituency Parser]]
  * Sequence-to-Sequence Constituency Parsing
    * [[https://papers.nips.cc/paper/5635-grammar-as-a-foreign-language.pdf|Vinyals et al 2015 - Grammar as a Foreign Language]]
    * [[https://aclanthology.org/P18-2097.pdf|Suzuki et al 2018 - An Empirical Study of Building a Strong Baseline for Constituency Parsing]]
  * Recurrent Neural Network Grammars (RNNG)
    * [[https://arxiv.org/pdf/1602.07776.pdf|Dyer et al 2016 - Recurrent Neural Network Grammars]]
  * Sequence labeling
    * [[https://arxiv.org/pdf/1810.08994.pdf|Gómez-Rodríguez & Vilares 2018 - Constituent Parsing as Sequence Labeling]]
  * Non-Parametric Bayesian Parsers
    * [[https://aclanthology.org/P12-1046.pdf|Shindo et al 2012 - Bayesian Symbol-Refined Tree Substitution Grammars for Syntactic Parsing]] 92.4 on PTB. Was SOTA until [[https://arxiv.org/pdf/1602.07776.pdf|Dyer 2016]] surpassed it.

===== Unsupervised Constituency Parsing =====

==== Overviews ====
  * [[https://www.aclweb.org/anthology/2020.acl-main.300.pdf|Li et al 2020 - An Empirical Comparison of Unsupervised Constituency Parsing Methods]]
  * **Good overview**: related work of [[https://www.aclweb.org/anthology/2020.tacl-1.15.pdf|Nishida 2020]] (Gives a good history of unsupervised parsing in the related work)

==== Papers ====
  * [[https://arxiv.org/pdf/2010.02423.pdf|Shi et al 2020 - On the Role of Supervision in Unsupervised Constituency Parsing]]
  * [[https://arxiv.org/pdf/2105.15021.pdf|Yang et al 2021 - Neural Bi-Lexicalized PCFG Induction]]
  * Image-Aided
  * Video-Aided
    * [[https://arxiv.org/pdf/2104.04369.pdf|Zhang et al 2021 - Video-aided Unsupervised Grammar Induction]] (Best paper at NAACL 2021)

===== People =====
  * [[https://scholar.google.com/citations?user=faXAgZQAAAAJ&hl=en|Zhenghua Li]]

===== Related Pages =====
  * [[Dependency Parsing]]