A fast and accurate dependency parser using neural networks

Danqi Chen, Christopher D. Manning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

832 Scopus citations

Abstract

Almost all current dependency parsers classify based on millions of sparse indicator features. Not only do these features generalize poorly, but the cost of feature computation restricts parsing speed significantly. In this work, we propose a novel way of learning a neural network classifier for use in a greedy, transition-based dependency parser. Because this classifier learns and uses just a small number of dense features, it can work very fast, while achieving an about 2% improvement in unlabeled and labeled attachment scores on both English and Chinese datasets. Concretely, our parser is able to parse more than 1000 sentences per second at 92.2% unlabeled attachment score on the English Penn Treebank.

Original languageEnglish (US)
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages740-750
Number of pages11
ISBN (Electronic)9781937284961
DOIs
StatePublished - Jan 1 2014
Externally publishedYes
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: Oct 25 2014Oct 29 2014

Publication series

NameEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period10/25/1410/29/14

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Fingerprint Dive into the research topics of 'A fast and accurate dependency parser using neural networks'. Together they form a unique fingerprint.

Cite this