<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-bhat-2021-idiomatic">
    <titleInfo>
        <title>Idiomatic Expression Identification using Semantic Compatibility</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziheng</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Suma</namePart>
        <namePart type="family">Bhat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Idiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, they have been a classical challenge for NLP systems. To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it when it occurs in a figurative sense. Prior research for this task has studied specific classes of idiomatic expressions offering limited views of their generalizability to new idioms. We propose a multi-stage neural architecture with attention flow as a solution. The network effectively fuses contextual and lexical information at different levels using word and sub-word representations. Empirical evaluations on three of the largest benchmark datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality show that our proposed model achieves new state-of-the-art results. A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset.</abstract>
    <identifier type="citekey">zeng-bhat-2021-idiomatic</identifier>
    <identifier type="doi">10.1162/tacl_a_00442</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.92</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>1546</start>
            <end>1562</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Idiomatic Expression Identification using Semantic Compatibility
%A Zeng, Ziheng
%A Bhat, Suma
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F zeng-bhat-2021-idiomatic
%X Idiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, they have been a classical challenge for NLP systems. To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it when it occurs in a figurative sense. Prior research for this task has studied specific classes of idiomatic expressions offering limited views of their generalizability to new idioms. We propose a multi-stage neural architecture with attention flow as a solution. The network effectively fuses contextual and lexical information at different levels using word and sub-word representations. Empirical evaluations on three of the largest benchmark datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality show that our proposed model achieves new state-of-the-art results. A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset.
%R 10.1162/tacl_a_00442
%U https://aclanthology.org/2021.tacl-1.92
%U https://doi.org/10.1162/tacl_a_00442
%P 1546-1562

Markdown (Informal)

[Idiomatic Expression Identification using Semantic Compatibility](https://aclanthology.org/2021.tacl-1.92) (Zeng & Bhat, TACL 2021)

• Idiomatic Expression Identification using Semantic Compatibility (Zeng & Bhat, TACL 2021)

ACL

• Ziheng Zeng and Suma Bhat. 2021. Idiomatic Expression Identification using Semantic Compatibility. Transactions of the Association for Computational Linguistics, 9:1546–1562.