@inproceedings{wang-etal-2024-vaegpt,
title = "{VAEGPT}-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising {VAE}",
author = "Wang, Zhenyi and
Ning, Haiyan and
Ling, Qing and
Wang, Dan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.513/",
doi = "10.18653/v1/2024.findings-acl.513",
pages = "8666--8681",
abstract = "Text embedding requires a highly efficient method for training domain-specific models on limited data, as general models trained on large corpora lack universal applicability in highly specific fields. Therefore, we have introduced VAEGPT-Sim, an innovative model for generating synonyms that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language. Even when trained with completely unsupervised settings, it maintains a harmonious balance between semantic similarity and lexical diversity, as shown by a comprehensive evaluation metric system with the highest average scores compared to other generative models. When VAEGPT-Sim is utilized as a module for contrastive learning in text representation, it delivers state-of-the-art results in small-dataset training on STS benchmarks, surpassing ConSERT by 2.8 points. This approach optimizes the effectiveness of text representation despite a limited corpus, signifying an advancement in domain-specific embedding technology."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-vaegpt">
<titleInfo>
<title>VAEGPT-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising VAE</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhenyi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyan</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</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>Text embedding requires a highly efficient method for training domain-specific models on limited data, as general models trained on large corpora lack universal applicability in highly specific fields. Therefore, we have introduced VAEGPT-Sim, an innovative model for generating synonyms that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language. Even when trained with completely unsupervised settings, it maintains a harmonious balance between semantic similarity and lexical diversity, as shown by a comprehensive evaluation metric system with the highest average scores compared to other generative models. When VAEGPT-Sim is utilized as a module for contrastive learning in text representation, it delivers state-of-the-art results in small-dataset training on STS benchmarks, surpassing ConSERT by 2.8 points. This approach optimizes the effectiveness of text representation despite a limited corpus, signifying an advancement in domain-specific embedding technology.</abstract>
<identifier type="citekey">wang-etal-2024-vaegpt</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.513</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.513/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8666</start>
<end>8681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VAEGPT-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising VAE
%A Wang, Zhenyi
%A Ning, Haiyan
%A Ling, Qing
%A Wang, Dan
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-vaegpt
%X Text embedding requires a highly efficient method for training domain-specific models on limited data, as general models trained on large corpora lack universal applicability in highly specific fields. Therefore, we have introduced VAEGPT-Sim, an innovative model for generating synonyms that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language. Even when trained with completely unsupervised settings, it maintains a harmonious balance between semantic similarity and lexical diversity, as shown by a comprehensive evaluation metric system with the highest average scores compared to other generative models. When VAEGPT-Sim is utilized as a module for contrastive learning in text representation, it delivers state-of-the-art results in small-dataset training on STS benchmarks, surpassing ConSERT by 2.8 points. This approach optimizes the effectiveness of text representation despite a limited corpus, signifying an advancement in domain-specific embedding technology.
%R 10.18653/v1/2024.findings-acl.513
%U https://aclanthology.org/2024.findings-acl.513/
%U https://doi.org/10.18653/v1/2024.findings-acl.513
%P 8666-8681
Markdown (Informal)
[VAEGPT-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising VAE](https://aclanthology.org/2024.findings-acl.513/) (Wang et al., Findings 2024)
ACL