<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2024-improving">
    <titleInfo>
        <title>Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soma</namePart>
        <namePart type="family">Sato</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hayato</namePart>
        <namePart type="family">Tsukagoshi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryohei</namePart>
        <namePart type="family">Sasano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Koichi</namePart>
        <namePart type="family">Takeda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Xiyan</namePart>
            <namePart type="family">Fu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Eve</namePart>
            <namePart type="family">Fleisig</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Decoder-based large language models (LLMs) have shown high performance on many tasks in natural language processing. This is also true for sentence embedding learning, where a decoder-based model, PromptEOL, has achieved the best performance on semantic textual similarity (STS) tasks. However, PromptEOL requires a manually annotated natural language inference (NLI) dataset for fine-tuning.We aim to improve sentence embeddings without using large manually annotated datasets by automatically generating an NLI dataset with an LLM and using it for fine-tuning of PromptEOL. To achieve this, we explore methods of data generation suitable for sentence embedding learning in this study. Specifically, we will focus on automatic dataset generation through few-shot learning and explore the appropriate methods to leverage few-shot examples. Experimental results on the STS tasks demonstrate that our approach outperforms existing models in settings without large manually annotated datasets.</abstract>
    <identifier type="citekey">sato-etal-2024-improving</identifier>
    <identifier type="doi">10.18653/v1/2024.acl-srw.43</identifier>
    <location>
        <url>https://aclanthology.org/2024.acl-srw.43</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>378</start>
            <end>389</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples
%A Sato, Soma
%A Tsukagoshi, Hayato
%A Sasano, Ryohei
%A Takeda, Koichi
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F sato-etal-2024-improving
%X Decoder-based large language models (LLMs) have shown high performance on many tasks in natural language processing. This is also true for sentence embedding learning, where a decoder-based model, PromptEOL, has achieved the best performance on semantic textual similarity (STS) tasks. However, PromptEOL requires a manually annotated natural language inference (NLI) dataset for fine-tuning.We aim to improve sentence embeddings without using large manually annotated datasets by automatically generating an NLI dataset with an LLM and using it for fine-tuning of PromptEOL. To achieve this, we explore methods of data generation suitable for sentence embedding learning in this study. Specifically, we will focus on automatic dataset generation through few-shot learning and explore the appropriate methods to leverage few-shot examples. Experimental results on the STS tasks demonstrate that our approach outperforms existing models in settings without large manually annotated datasets.
%R 10.18653/v1/2024.acl-srw.43
%U https://aclanthology.org/2024.acl-srw.43
%U https://doi.org/10.18653/v1/2024.acl-srw.43
%P 378-389

Markdown (Informal)

[Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples](https://aclanthology.org/2024.acl-srw.43) (Sato et al., ACL 2024)

• Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples (Sato et al., ACL 2024)

ACL

• Soma Sato, Hayato Tsukagoshi, Ryohei Sasano, and Koichi Takeda. 2024. Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 378–389, Bangkok, Thailand. Association for Computational Linguistics.