Dependency Parsing

277 papers with code • 14 benchmarks • 12 datasets

Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between "head" words and words, which modify those heads.


      | +-------dobj---------+
      | |                    |
nsubj | |   +------det-----+ | +-----nmod------+
+--+  | |   |              | | |               |
|  |  | |   |      +-nmod-+| | |      +-case-+ |
+  |  + |   +      +      || + |      +      | |
I  prefer  the  morning   flight  through  Denver

Relations among the words are illustrated above the sentence with directed, labeled arcs from heads to dependents (+ indicates the dependent).


Use these libraries to find Dependency Parsing models and implementations

Most implemented papers

Deep Biaffine Attention for Neural Dependency Parsing

PaddlePaddle/PaddleNLP 6 Nov 2016

This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser.

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

clab/lstm-parser IJCNLP 2015

We propose a technique for learning representations of parser states in transition-based dependency parsers.

CamemBERT: a Tasty French Language Model

huggingface/transformers ACL 2020

We show that the use of web crawled data is preferable to the use of Wikipedia data.

SciBERT: A Pretrained Language Model for Scientific Text

allenai/scibert IJCNLP 2019

Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive.

Second-Order Semantic Dependency Parsing with End-to-End Neural Networks

wangxinyu0922/Second_Order_SDP ACL 2019

Semantic dependency parsing aims to identify semantic relationships between words in a sentence that form a graph.

Stanza: A Python Natural Language Processing Toolkit for Many Human Languages

stanfordnlp/stanza ACL 2020

We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages.

DisSent: Sentence Representation Learning from Explicit Discourse Relations

facebookresearch/InferSent 12 Oct 2017

Learning effective representations of sentences is one of the core missions of natural language understanding.

SparseMAP: Differentiable Sparse Structured Inference

vene/sparsemap ICML 2018

Structured prediction requires searching over a combinatorial number of structures.

Stack-Pointer Networks for Dependency Parsing

XuezheMax/NeuroNLP2 ACL 2018

Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion.

Simpler but More Accurate Semantic Dependency Parsing

yzhangcs/parser ACL 2018

While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations.