<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-liu-2023-adversarial">
    <titleInfo>
        <title>Adversarial Multi-task Learning for End-to-end Metaphor Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shenglong</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ying</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word sense disambiguation (WSD), which has copious amounts of data. We leverage adversarial training to align the data distributions of MD and BSD in the same feature space, so task-invariant representations can be learned. To capture fine-grained alignment patterns, we utilize the multi-mode structures of MD and BSD. Our method is totally end-to-end and can mitigate the data scarcity problem in MD. Competitive results are reported on four public datasets. Our code and datasets are available.</abstract>
    <identifier type="citekey">zhang-liu-2023-adversarial</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.96</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.96</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1483</start>
            <end>1497</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adversarial Multi-task Learning for End-to-end Metaphor Detection
%A Zhang, Shenglong
%A Liu, Ying
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-liu-2023-adversarial
%X Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word sense disambiguation (WSD), which has copious amounts of data. We leverage adversarial training to align the data distributions of MD and BSD in the same feature space, so task-invariant representations can be learned. To capture fine-grained alignment patterns, we utilize the multi-mode structures of MD and BSD. Our method is totally end-to-end and can mitigate the data scarcity problem in MD. Competitive results are reported on four public datasets. Our code and datasets are available.
%R 10.18653/v1/2023.findings-acl.96
%U https://aclanthology.org/2023.findings-acl.96
%U https://doi.org/10.18653/v1/2023.findings-acl.96
%P 1483-1497

Markdown (Informal)

[Adversarial Multi-task Learning for End-to-end Metaphor Detection](https://aclanthology.org/2023.findings-acl.96) (Zhang & Liu, Findings 2023)

• Adversarial Multi-task Learning for End-to-end Metaphor Detection (Zhang & Liu, Findings 2023)

ACL

• Shenglong Zhang and Ying Liu. 2023. Adversarial Multi-task Learning for End-to-end Metaphor Detection. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1483–1497, Toronto, Canada. Association for Computational Linguistics.