<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mizuki-okazaki-2023-semantic">
    <titleInfo>
        <title>Semantic Specialization for Knowledge-based Word Sense Disambiguation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sakae</namePart>
        <namePart type="family">Mizuki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoaki</namePart>
        <namePart type="family">Okazaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a target word in a given sentence. This approach relies on the similarity of the sense and context embeddings computed by a pre-trained language model. We propose a semantic specialization for WSD where contextualized embeddings are adapted to the WSD task using solely lexical knowledge. The key idea is, for a given sense, to bring semantically related senses and contexts closer and send different/unrelated senses farther away. We realize this idea as the joint optimization of the Attract-Repel objective for sense pairs and the self-training objective for context-sense pairs while controlling deviations from the original embeddings. The proposed method outperformed previous studies that adapt contextualized embeddings. It achieved state-of-the-art performance on knowledge-based WSD when combined with the reranking heuristic that uses the sense inventory. We found that the similarity characteristics of specialized embeddings conform to the key idea. We also found that the (dis)similarity of embeddings between the related/different/unrelated senses correlates well with the performance of WSD.</abstract>
    <identifier type="citekey">mizuki-okazaki-2023-semantic</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.251</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.251</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>3457</start>
            <end>3470</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semantic Specialization for Knowledge-based Word Sense Disambiguation
%A Mizuki, Sakae
%A Okazaki, Naoaki
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F mizuki-okazaki-2023-semantic
%X A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a target word in a given sentence. This approach relies on the similarity of the sense and context embeddings computed by a pre-trained language model. We propose a semantic specialization for WSD where contextualized embeddings are adapted to the WSD task using solely lexical knowledge. The key idea is, for a given sense, to bring semantically related senses and contexts closer and send different/unrelated senses farther away. We realize this idea as the joint optimization of the Attract-Repel objective for sense pairs and the self-training objective for context-sense pairs while controlling deviations from the original embeddings. The proposed method outperformed previous studies that adapt contextualized embeddings. It achieved state-of-the-art performance on knowledge-based WSD when combined with the reranking heuristic that uses the sense inventory. We found that the similarity characteristics of specialized embeddings conform to the key idea. We also found that the (dis)similarity of embeddings between the related/different/unrelated senses correlates well with the performance of WSD.
%R 10.18653/v1/2023.eacl-main.251
%U https://aclanthology.org/2023.eacl-main.251
%U https://doi.org/10.18653/v1/2023.eacl-main.251
%P 3457-3470

Markdown (Informal)

[Semantic Specialization for Knowledge-based Word Sense Disambiguation](https://aclanthology.org/2023.eacl-main.251) (Mizuki & Okazaki, EACL 2023)

• Semantic Specialization for Knowledge-based Word Sense Disambiguation (Mizuki & Okazaki, EACL 2023)

ACL

• Sakae Mizuki and Naoaki Okazaki. 2023. Semantic Specialization for Knowledge-based Word Sense Disambiguation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3457–3470, Dubrovnik, Croatia. Association for Computational Linguistics.