<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-yu-2023-going">
    <titleInfo>
        <title>Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongwei</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dong</namePart>
        <namePart type="family">Yu</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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>Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent. State-of-the-art methods for STS task use language models to encode sentences into embeddings. However, these embeddings are limited in representing semantics because they mix all the semantic information together in fixed-length vectors, which are difficult to recover and lack explainability. This paper presents a token-level matching inference algorithm, which can be applied on top of any language model to improve its performance on STS task. Our method calculates pairwise token-level similarity and token matching scores, and then aggregates them with pretrained token weights to produce sentence similarity. Experimental results on seven STS datasets show that our method improves the performance of almost all language models, with up to 12.7% gain in Spearman’s correlation. We also demonstrate that our method is highly explainable and computationally efficient.</abstract>
    <identifier type="citekey">wang-yu-2023-going</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-short.49</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-short.49</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>563</start>
            <end>570</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity
%A Wang, Hongwei
%A Yu, Dong
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-yu-2023-going
%X Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent. State-of-the-art methods for STS task use language models to encode sentences into embeddings. However, these embeddings are limited in representing semantics because they mix all the semantic information together in fixed-length vectors, which are difficult to recover and lack explainability. This paper presents a token-level matching inference algorithm, which can be applied on top of any language model to improve its performance on STS task. Our method calculates pairwise token-level similarity and token matching scores, and then aggregates them with pretrained token weights to produce sentence similarity. Experimental results on seven STS datasets show that our method improves the performance of almost all language models, with up to 12.7% gain in Spearman’s correlation. We also demonstrate that our method is highly explainable and computationally efficient.
%R 10.18653/v1/2023.acl-short.49
%U https://aclanthology.org/2023.acl-short.49
%U https://doi.org/10.18653/v1/2023.acl-short.49
%P 563-570

Markdown (Informal)

[Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity](https://aclanthology.org/2023.acl-short.49) (Wang & Yu, ACL 2023)

• Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity (Wang & Yu, ACL 2023)

ACL

• Hongwei Wang and Dong Yu. 2023. Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 563–570, Toronto, Canada. Association for Computational Linguistics.