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

@inproceedings{Dyer2015TransitionBasedDP,
  title={Transition-Based Dependency Parsing with Stack Long Short-Term Memory},
  author={Chris Dyer and Miguel Ballesteros and Wang Ling and Austin Matthews and Noah A. Smith},
  booktitle={ACL},
  year={2015}
}
We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks---the stack LSTM. Like the conventional stack data structures used in transition-based parsing, elements can be pushed to or popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. This lets us formulate an efficient… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 456 CITATIONS

Syntactic Inductive Biases for Natural Language Processing

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Neural Transition-based Model for Nested Mention Recognition

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing

Aaron Smith, Miryam de Lhoneux, Sara Stymne, Joakim Nivre
  • EMNLP
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

End-to-end Answer Selection via Attention-Based Bi-LSTM Network

  • 2018 1st IEEE International Conference on Hot Information-Centric Networking (HotICN)
  • 2018
VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Neural Syntactic Generative Models with Exact Marginalization

  • NAACL-HLT
  • 2018
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Dependency Parsing for Tweets

  • 2017
VIEW 18 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Encoder-Decoder Shift-Reduce Syntactic Parsing

VIEW 25 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 79 Highly Influenced Citations

  • Averaged 105 Citations per year from 2017 through 2019