<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marasovic-frank-2018-srl4orl">
    <titleInfo>
        <title>SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ana</namePart>
        <namePart type="family">Marasović</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anette</namePart>
        <namePart type="family">Frank</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marilyn</namePart>
            <namePart type="family">Walker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Heng</namePart>
            <namePart type="family">Ji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amanda</namePart>
            <namePart type="family">Stent</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>For over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question “Who expressed what kind of sentiment towards what?”. Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL). We suspect this is due to the scarcity of labeled training data and address this issue using different multi-task learning (MTL) techniques with a related task which has substantially more data, i.e. Semantic Role Labeling (SRL). We show that two MTL models improve significantly over the single-task model for labeling of both holders and targets, on the development and the test sets. We found that the vanilla MTL model, which makes predictions using only shared ORL and SRL features, performs the best. With deeper analysis we determine what works and what might be done to make further improvements for ORL.</abstract>
    <identifier type="citekey">marasovic-frank-2018-srl4orl</identifier>
    <identifier type="doi">10.18653/v1/N18-1054</identifier>
    <location>
        <url>https://aclanthology.org/N18-1054</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>583</start>
            <end>594</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling
%A Marasović, Ana
%A Frank, Anette
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F marasovic-frank-2018-srl4orl
%X For over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question “Who expressed what kind of sentiment towards what?”. Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL). We suspect this is due to the scarcity of labeled training data and address this issue using different multi-task learning (MTL) techniques with a related task which has substantially more data, i.e. Semantic Role Labeling (SRL). We show that two MTL models improve significantly over the single-task model for labeling of both holders and targets, on the development and the test sets. We found that the vanilla MTL model, which makes predictions using only shared ORL and SRL features, performs the best. With deeper analysis we determine what works and what might be done to make further improvements for ORL.
%R 10.18653/v1/N18-1054
%U https://aclanthology.org/N18-1054
%U https://doi.org/10.18653/v1/N18-1054
%P 583-594

Markdown (Informal)

[SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling](https://aclanthology.org/N18-1054) (Marasović & Frank, NAACL 2018)

• SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling (Marasović & Frank, NAACL 2018)

ACL

• Ana Marasović and Anette Frank. 2018. SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 583–594, New Orleans, Louisiana. Association for Computational Linguistics.