@inproceedings{che-etal-2017-hit,
title = "The {HIT}-{SCIR} System for End-to-End Parsing of {U}niversal {D}ependencies",
author = "Che, Wanxiang and
Guo, Jiang and
Wang, Yuxuan and
Zheng, Bo and
Zhao, Huaipeng and
Liu, Yang and
Teng, Dechuan and
Liu, Ting",
editor = "Haji{\v{c}}, Jan and
Zeman, Dan",
booktitle = "Proceedings of the {C}o{NLL} 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K17-3005",
doi = "10.18653/v1/K17-3005",
pages = "52--62",
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: \textit{tokenization}, \textit{Part-of-Speech} (POS) \textit{tagging} and \textit{dependency parsing}. We use character-based bidirectional long short-term memory (LSTM) networks for both tokenization and POS tagging. Afterwards, 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="che-etal-2017-hit">
<titleInfo>
<title>The HIT-SCIR System for End-to-End Parsing of Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaipeng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dechuan</namePart>
<namePart type="family">Teng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hajič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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. Afterwards, 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.</abstract>
<identifier type="citekey">che-etal-2017-hit</identifier>
<identifier type="doi">10.18653/v1/K17-3005</identifier>
<location>
<url>https://aclanthology.org/K17-3005</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>52</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The HIT-SCIR System for End-to-End Parsing of Universal Dependencies
%A Che, Wanxiang
%A Guo, Jiang
%A Wang, Yuxuan
%A Zheng, Bo
%A Zhao, Huaipeng
%A Liu, Yang
%A Teng, Dechuan
%A Liu, Ting
%Y Hajič, Jan
%Y Zeman, Dan
%S Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F che-etal-2017-hit
%X 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. Afterwards, 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.
%R 10.18653/v1/K17-3005
%U https://aclanthology.org/K17-3005
%U https://doi.org/10.18653/v1/K17-3005
%P 52-62
Markdown (Informal)
[The HIT-SCIR System for End-to-End Parsing of Universal Dependencies](https://aclanthology.org/K17-3005) (Che et al., CoNLL 2017)
ACL
- Wanxiang Che, Jiang Guo, Yuxuan Wang, Bo Zheng, Huaipeng Zhao, Yang Liu, Dechuan Teng, and Ting Liu. 2017. The HIT-SCIR System for End-to-End Parsing of Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 52–62, Vancouver, Canada. Association for Computational Linguistics.