Constituency Parsing

Constituency parsing aims to extract a constituency-based parse tree from a sentence that represents its syntactic structure according to a phrase structure grammar.

Example:

             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)).

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–204 of 204 papers

Title	Date	Tasks	Status
Neural Machine Translation with Synchronous Latent Phrase Structure	Aug 1, 2021	Constituency ParsingDecoder	—Unverified
Online Learning for Inexact Hypergraph Search	Oct 1, 2013	Constituency ParsingStructured Prediction	—Unverified
On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations	Jan 27, 2021	Constituency ParsingPOS	—Unverified
On the Role of Supervision in Unsupervised Constituency Parsing	Oct 6, 2020	Constituency ParsingData Augmentation	—Unverified

Show:10 25 50

← PrevPage 5 of 5Next →

All datasets Penn Treebank CTB5 CTB7 ATB

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Hashing + XLNet	F1 score	96.43	—	Unverified
2	SAPar + XLNet	F1 score	96.4	—	Unverified
3	Label Attention Layer + HPSG + XLNet	F1 score	96.38	—	Unverified
4	Attach-Juxtapose Parser + XLNet	F1 score	96.34	—	Unverified
5	Head-Driven Phrase Structure Grammar Parsing (Joint) + XLNet	F1 score	96.33	—	Unverified
6	CRF Parser + RoBERTa	F1 score	96.32	—	Unverified
7	Hashing + Bert	F1 score	96.03	—	Unverified
8	NFC + BERT-large	F1 score	95.92	—	Unverified
9	N-ary semi-markov + BERT-large	F1 score	95.92	—	Unverified
10	Head-Driven Phrase Structure Grammar Parsing (Joint) + BERT	F1 score	95.84	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Attach-Juxtapose Parser + BERT	F1 score	93.52	—	Unverified
2	SAPar + BERT	F1 score	92.66	—	Unverified
3	N-ary semi-markov + BERT	F1 score	92.5	—	Unverified
4	Hashing + Bert	F1 score	92.33	—	Unverified
5	CRF Parser + BERT	F1 score	92.27	—	Unverified
6	Kitaev etal. 2019	F1 score	91.75	—	Unverified
7	CRF Parser	F1 score	89.8	—	Unverified
8	Zhou etal. 2019	F1 score	89.4	—	Unverified
9	Kitaev etal. 2018	F1 score	87.43	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CRF Parser + Electra	F1 score	91.92	—	Unverified
2	CRF Parser + BERT	F1 score	91.55	—	Unverified
3	CRF Parser	F1 score	88.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SAPar	F1	83.26	—	Unverified