<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="che-etal-2019-hit">
    <titleInfo>
        <title>HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding</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">Longxu</namePart>
        <namePart type="family">Dou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Xu</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">Yijia</namePart>
        <namePart type="family">Liu</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>2019-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. We extended the basic transition-based parser with two improvements: a) Efficient Training by realizing Stack LSTM parallel training; b) Effective Encoding via adopting deep contextualized word embeddings BERT. Generally, we proposed a unified pipeline to meaning representation parsing, including framework-specific transition-based parsers, BERT-enhanced word representation, and post-processing. In the final evaluation, our system was ranked first according to ALL-F1 (86.2%) and especially ranked first in UCCA framework (81.67%).</abstract>
    <identifier type="citekey">che-etal-2019-hit</identifier>
    <identifier type="doi">10.18653/v1/K19-2007</identifier>
    <location>
        <url>https://aclanthology.org/K19-2007</url>
    </location>
    <part>
        <date>2019-nov</date>
        <extent unit="page">
            <start>76</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding
%A Che, Wanxiang
%A Dou, Longxu
%A Xu, Yang
%A Wang, Yuxuan
%A Liu, Yijia
%A Liu, Ting
%S Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong
%F che-etal-2019-hit
%X This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. We extended the basic transition-based parser with two improvements: a) Efficient Training by realizing Stack LSTM parallel training; b) Effective Encoding via adopting deep contextualized word embeddings BERT. Generally, we proposed a unified pipeline to meaning representation parsing, including framework-specific transition-based parsers, BERT-enhanced word representation, and post-processing. In the final evaluation, our system was ranked first according to ALL-F1 (86.2%) and especially ranked first in UCCA framework (81.67%).
%R 10.18653/v1/K19-2007
%U https://aclanthology.org/K19-2007
%U https://doi.org/10.18653/v1/K19-2007
%P 76-85

Markdown (Informal)

[HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding](https://aclanthology.org/K19-2007) (Che et al., CoNLL 2019)

• HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding (Che et al., CoNLL 2019)

ACL

• Wanxiang Che, Longxu Dou, Yang Xu, Yuxuan Wang, Yijia Liu, and Ting Liu. 2019. HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 76–85, Hong Kong. Association for Computational Linguistics.