<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-lapata-2017-learning">
    <titleInfo>
        <title>Learning Contextually Informed Representations for Linear-Time Discourse Parsing</title>
    </titleInfo>
    <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">Mirella</namePart>
        <namePart type="family">Lapata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent advances in RST discourse parsing have focused on two modeling paradigms: (a) high order parsers which jointly predict the tree structure of the discourse and the relations it encodes; or (b) linear-time parsers which are efficient but mostly based on local features. In this work, we propose a linear-time parser with a novel way of representing discourse constituents based on neural networks which takes into account global contextual information and is able to capture long-distance dependencies. Experimental results show that our parser obtains state-of-the art performance on benchmark datasets, while being efficient (with time complexity linear in the number of sentences in the document) and requiring minimal feature engineering.</abstract>
    <identifier type="citekey">liu-lapata-2017-learning</identifier>
    <identifier type="doi">10.18653/v1/D17-1133</identifier>
    <location>
        <url>https://aclanthology.org/D17-1133</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>1289</start>
            <end>1298</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Contextually Informed Representations for Linear-Time Discourse Parsing
%A Liu, Yang
%A Lapata, Mirella
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F liu-lapata-2017-learning
%X Recent advances in RST discourse parsing have focused on two modeling paradigms: (a) high order parsers which jointly predict the tree structure of the discourse and the relations it encodes; or (b) linear-time parsers which are efficient but mostly based on local features. In this work, we propose a linear-time parser with a novel way of representing discourse constituents based on neural networks which takes into account global contextual information and is able to capture long-distance dependencies. Experimental results show that our parser obtains state-of-the art performance on benchmark datasets, while being efficient (with time complexity linear in the number of sentences in the document) and requiring minimal feature engineering.
%R 10.18653/v1/D17-1133
%U https://aclanthology.org/D17-1133
%U https://doi.org/10.18653/v1/D17-1133
%P 1289-1298

Markdown (Informal)

[Learning Contextually Informed Representations for Linear-Time Discourse Parsing](https://aclanthology.org/D17-1133) (Liu & Lapata, EMNLP 2017)

• Learning Contextually Informed Representations for Linear-Time Discourse Parsing (Liu & Lapata, EMNLP 2017)

ACL

• Yang Liu and Mirella Lapata. 2017. Learning Contextually Informed Representations for Linear-Time Discourse Parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1289–1298, Copenhagen, Denmark. Association for Computational Linguistics.