<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oda-etal-2026-one">
    <titleInfo>
        <title>One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kohei</namePart>
        <namePart type="family">Oda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Po-Min</namePart>
        <namePart type="family">Chuang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kiyoaki</namePart>
        <namePart type="family">Shirai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Natthawut</namePart>
        <namePart type="family">Kertkeidkachorn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign only a single vector per sentence. To overcome this limitation, we propose DualCSE, a sentence embedding method that assigns two embeddings to each sentence: one representing the explicit semantics and the other representing the implicit semantics. These embeddings coexist in the shared space, enabling the selection of the desired semantics for specific purposes such as information retrieval and text classification. Experimental results demonstrate that DualCSE can effectively encode both explicit and implicit meanings and improve the performance of the downstream task.</abstract>
    <identifier type="citekey">oda-etal-2026-one</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.74/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1444</start>
            <end>1452</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
%A Oda, Kohei
%A Chuang, Po-Min
%A Shirai, Kiyoaki
%A Kertkeidkachorn, Natthawut
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F oda-etal-2026-one
%X Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign only a single vector per sentence. To overcome this limitation, we propose DualCSE, a sentence embedding method that assigns two embeddings to each sentence: one representing the explicit semantics and the other representing the implicit semantics. These embeddings coexist in the shared space, enabling the selection of the desired semantics for specific purposes such as information retrieval and text classification. Experimental results demonstrate that DualCSE can effectively encode both explicit and implicit meanings and improve the performance of the downstream task.
%U https://aclanthology.org/2026.findings-eacl.74/
%P 1444-1452

Markdown (Informal)

[One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations](https://aclanthology.org/2026.findings-eacl.74/) (Oda et al., Findings 2026)

• One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations (Oda et al., Findings 2026)

ACL

• Kohei Oda, Po-Min Chuang, Kiyoaki Shirai, and Natthawut Kertkeidkachorn. 2026. One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations. In Findings of the Association for Computational Linguistics: EACL 2026, pages 1444–1452, Rabat, Morocco. Association for Computational Linguistics.