<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-learning">
    <titleInfo>
        <title>Learning High-Quality and General-Purpose Phrase Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lihu</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gael</namePart>
        <namePart type="family">Varoquaux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabian</namePart>
        <namePart type="family">Suchanek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification.The current state-of-the-art method involves fine-tuning pre-trained language models for phrasal embeddings using contrastive learning. However, we have identified areas for improvement. First, these pre-trained models tend to be unnecessarily complex and require to be pre-trained on a corpus with context sentences.Second, leveraging the phrase type and morphology gives phrase representations that are both more precise and more flexible.We propose an improved framework to learn phrase representations in a context-free fashion.The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation.Furthermore, we design three granularities of data augmentation to increase the diversity of training samples.Our experiments across a wide range of tasks reveal that our approach generates superior phrase embeddings compared to previous methods while requiring a smaller model size.</abstract>
    <identifier type="citekey">chen-etal-2024-learning</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-eacl.66</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>983</start>
            <end>994</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning High-Quality and General-Purpose Phrase Representations
%A Chen, Lihu
%A Varoquaux, Gael
%A Suchanek, Fabian
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F chen-etal-2024-learning
%X Phrase representations play an important role in data science and natural language processing, benefiting various tasks like Entity Alignment, Record Linkage, Fuzzy Joins, and Paraphrase Classification.The current state-of-the-art method involves fine-tuning pre-trained language models for phrasal embeddings using contrastive learning. However, we have identified areas for improvement. First, these pre-trained models tend to be unnecessarily complex and require to be pre-trained on a corpus with context sentences.Second, leveraging the phrase type and morphology gives phrase representations that are both more precise and more flexible.We propose an improved framework to learn phrase representations in a context-free fashion.The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation.Furthermore, we design three granularities of data augmentation to increase the diversity of training samples.Our experiments across a wide range of tasks reveal that our approach generates superior phrase embeddings compared to previous methods while requiring a smaller model size.
%U https://aclanthology.org/2024.findings-eacl.66
%P 983-994

Markdown (Informal)

[Learning High-Quality and General-Purpose Phrase Representations](https://aclanthology.org/2024.findings-eacl.66) (Chen et al., Findings 2024)

• Learning High-Quality and General-Purpose Phrase Representations (Chen et al., Findings 2024)

ACL

• Lihu Chen, Gael Varoquaux, and Fabian Suchanek. 2024. Learning High-Quality and General-Purpose Phrase Representations. In Findings of the Association for Computational Linguistics: EACL 2024, pages 983–994, St. Julian’s, Malta. Association for Computational Linguistics.