<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yong-torrent-2020-semi">
    <titleInfo>
        <title>Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="given">Xin</namePart>
        <namePart type="family">Yong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tiago</namePart>
        <namePart type="given">Timponi</namePart>
        <namePart type="family">Torrent</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">English</languageTerm>
        <languageTerm type="code" authority="iso639-2b">eng</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <originInfo>
            <publisher>European Language Resources Association</publisher>
            <place>
                <placeTerm type="text">Marseille, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-10-95546-34-4</identifier>
    </relatedItem>
    <abstract>Although FrameNet is recognized as one of the most fine-grained lexical databases, its coverage of lexical units is still limited. To tackle this issue, we propose a two-step frame induction process: for a set of lexical units not yet present in Berkeley FrameNet data release 1.7, first remove those that cannot fit into any existing semantic frame in FrameNet; then, assign the remaining lexical units to their correct frames. We also present the Semi-supervised Deep Embedded Clustering with Anomaly Detection (SDEC-AD) model—an algorithm that maps high-dimensional contextualized vector representations of lexical units to a low-dimensional latent space for better frame prediction and uses reconstruction error to identify lexical units that cannot evoke frames in FrameNet. SDEC-AD outperforms the state-of-the-art methods in both steps of the frame induction process. Empirical results also show that definitions provide contextual information for representing and characterizing the frame membership of lexical units.</abstract>
    <identifier type="citekey">yong-torrent-2020-semi</identifier>
    <location>
        <url>https://aclanthology.org/2020.lrec-1.431</url>
    </location>
    <part>
        <date>2020-05</date>
        <extent unit="page">
            <start>3509</start>
            <end>3519</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction
%A Yong, Zheng Xin
%A Torrent, Tiago Timponi
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F yong-torrent-2020-semi
%X Although FrameNet is recognized as one of the most fine-grained lexical databases, its coverage of lexical units is still limited. To tackle this issue, we propose a two-step frame induction process: for a set of lexical units not yet present in Berkeley FrameNet data release 1.7, first remove those that cannot fit into any existing semantic frame in FrameNet; then, assign the remaining lexical units to their correct frames. We also present the Semi-supervised Deep Embedded Clustering with Anomaly Detection (SDEC-AD) model—an algorithm that maps high-dimensional contextualized vector representations of lexical units to a low-dimensional latent space for better frame prediction and uses reconstruction error to identify lexical units that cannot evoke frames in FrameNet. SDEC-AD outperforms the state-of-the-art methods in both steps of the frame induction process. Empirical results also show that definitions provide contextual information for representing and characterizing the frame membership of lexical units.
%U https://aclanthology.org/2020.lrec-1.431
%P 3509-3519

Markdown (Informal)

[Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction](https://aclanthology.org/2020.lrec-1.431) (Yong & Torrent, LREC 2020)

• Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction (Yong & Torrent, LREC 2020)

ACL

• Zheng Xin Yong and Tiago Timponi Torrent. 2020. Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3509–3519, Marseille, France. European Language Resources Association.