Skip to main navigation Skip to search Skip to main content

The HIT-SCIR system for end-to-end parsing of universal dependencies

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes our system (HIT-SCIR) for the CoNLL 2017 shared task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system includes three pipelined components: tokenization, Part-of-Speech (POS) tagging and dependency parsing. We use character-based bidirectional long short-term memory (LSTM) networks for both tokenization and POS tagging. After-wards, we employ a list-based transition-based algorithm for general non-projective parsing and present an improved Stack-LSTM-based architecture for representing each transition state and making predictions. Furthermore, to parse low/zero-resource languages and cross-domain data, we use a model transfer approach to make effective use of existing resources. We demonstrate substantial gains against the UDPipe baseline, with an average improvement of 3.76% in LAS of all languages. And finally, we rank the 4th place on the official test sets.

Original languageEnglish
Title of host publicationCoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task
Subtitle of host publicationMultilingual Parsing from Raw Text to Universal Dependencies
PublisherAssociation for Computational Linguistics (ACL)
Pages52-62
Number of pages11
ISBN (Electronic)9781945626708
DOIs
StatePublished - 2017
Event2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017 - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017

Publication series

NameCoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Conference

Conference2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017
Country/TerritoryCanada
CityVancouver
Period3/08/174/08/17

Fingerprint

Dive into the research topics of 'The HIT-SCIR system for end-to-end parsing of universal dependencies'. Together they form a unique fingerprint.

Cite this