Constituency Parsing
73 papers with code • 4 benchmarks • 6 datasets
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)).
Benchmarks
These leaderboards are used to track progress in Constituency Parsing
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Penn Treebank
FLUE
Taiga Corpus
Most implemented papers
Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference
We present a constituency parsing algorithm that, like a supertagger, works by assigning labels to each word in a sentence.
Rethinking Self-Attention: Towards Interpretability in Neural Parsing
KhalilMrini/LAL-Parser
•
•
Findings of the Association for Computational Linguistics 2020
Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.
Fast and Accurate Neural CRF Constituency Parsing
yzhangcs/crfpar
•
•
IJCAI 2020
Estimating probability distribution is one of the core issues in the NLP field.
Converting the Point of View of Messages Spoken to Virtual Assistants
CopyNet was the most natural, with a relative perplexity of 1. 59.
StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling
google-research/google-research
•
•
ACL 2021
There are two major classes of natural language grammar -- the dependency grammar that models one-to-one correspondences between words and the constituency grammar that models the assembly of one or several corresponded words.
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
epfl-dlab/gcd
•
•
In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general.
Effective Self-Training for Parsing
We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data.
