Consituency parsing aims to extract a constituency-based parse tree from a sentence that represents its syntactic structure according to a phrase structure grammar.
Sentence (S) | +-------------+------------+ | | Noun (N) Verb Phrase (VP) | | John +-------+--------+ | | Verb (V) Noun (N) | | sees Bill
Recent approaches convert the parse tree into a sequence following a depth-first traversal in order to be able to apply sequence-to-sequence models to it. The linearized version of the above parse tree looks as follows: (S (N) (VP V N)).
The Wall Street Journal section of the Penn Treebank is used for evaluating constituency parsers. Section 22 is used for development and Section 23 is used for evaluation. Models are evaluated based on F1. Most of the below models incorporate external data or features. For a comparison of single models trained only on WSJ, refer to Kitaev and Klein (2018).
|Model||F1 score||Paper / Source|
|Self-attentive encoder + ELMo by Kitaev and Klein (2018)||95.13||Constituency Parsing with a Self-Attentive Encoder|
|Model combination by Fried et al. (2017)||94.66||Improving Neural Parsing by Disentangling Model Combination and Reranking Effects|
|In-order by Liu and Zhang (2017)||94.2||In-Order Transition-based Constituent Parsing|
|Semi-supervised LSTM-LM by Choe and Charniak (2016)||93.8||Parsing as Language Modeling|
|Stack-only RNNG by Kuncoro et al. (2017)||93.6||What Do Recurrent Neural Network Grammars Learn About Syntax?|
|RNN Grammar by Dyer et al. (2016)||93.3||Recurrent Neural Network Grammars|
|Transformer by Vaswani et al. (2017)||92.7||Attention Is All You Need|
|Semi-supervised LSTM by Vinyals et al. (2015)||92.1||Grammar as a Foreign Language|
|Self-trained parser by McClosky et al. (2006)||92.1||Effective Self-Training for Parsing|
Kitaev and Klein (2018)
Fried et al. (2017)
Liu and Zhang (2017)
Choe and Charniak (2016)
Kuncoro et al. (2017)
Dyer et al. (2016)
Vaswani et al. (2017)
Vinyals et al. (2015)
McClosky et al. (2006)