@inproceedings{yu-etal-2024-multi,
title = "Multi-Granularity Fusion Text Semantic Matching Based on {W}o{BERT}",
author = "Yu, Hongchun and
Pan, Wei and
Fan, Xing and
Li, Hanqi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1027",
pages = "11766--11775",
abstract = "Text semantic matching is crucial in natural language processing, applied in information retrieval, question answering, and recommendation systems. Traditional text-matching methods struggle with semantic nuances in short text. Recent advancements in multi-granularity representation learning have led to increased interest in improving text semantic matching models. We propose a novel multi-granularity fusion model that harnesses WoBERT, a pre-trained language model, to enhance the accuracy of text semantic information capture. Initially, we process text using WoBERT to acquire semantic representations, effectively capturing individual text semantic nuances. Next, we employ a soft attention alignment mechanism, enabling multi-granularity fusions among characters, words, and sentences, thus further improving matching performance. Our approach was evaluated through experiments on common Chinese short text matching datasets, BQ and LCQMC. Results reveal a significant improvement in performance compared to traditional methods, particularly in terms of accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2024-multi">
<titleInfo>
<title>Multi-Granularity Fusion Text Semantic Matching Based on WoBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongchun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text semantic matching is crucial in natural language processing, applied in information retrieval, question answering, and recommendation systems. Traditional text-matching methods struggle with semantic nuances in short text. Recent advancements in multi-granularity representation learning have led to increased interest in improving text semantic matching models. We propose a novel multi-granularity fusion model that harnesses WoBERT, a pre-trained language model, to enhance the accuracy of text semantic information capture. Initially, we process text using WoBERT to acquire semantic representations, effectively capturing individual text semantic nuances. Next, we employ a soft attention alignment mechanism, enabling multi-granularity fusions among characters, words, and sentences, thus further improving matching performance. Our approach was evaluated through experiments on common Chinese short text matching datasets, BQ and LCQMC. Results reveal a significant improvement in performance compared to traditional methods, particularly in terms of accuracy.</abstract>
<identifier type="citekey">yu-etal-2024-multi</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1027</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11766</start>
<end>11775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Granularity Fusion Text Semantic Matching Based on WoBERT
%A Yu, Hongchun
%A Pan, Wei
%A Fan, Xing
%A Li, Hanqi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yu-etal-2024-multi
%X Text semantic matching is crucial in natural language processing, applied in information retrieval, question answering, and recommendation systems. Traditional text-matching methods struggle with semantic nuances in short text. Recent advancements in multi-granularity representation learning have led to increased interest in improving text semantic matching models. We propose a novel multi-granularity fusion model that harnesses WoBERT, a pre-trained language model, to enhance the accuracy of text semantic information capture. Initially, we process text using WoBERT to acquire semantic representations, effectively capturing individual text semantic nuances. Next, we employ a soft attention alignment mechanism, enabling multi-granularity fusions among characters, words, and sentences, thus further improving matching performance. Our approach was evaluated through experiments on common Chinese short text matching datasets, BQ and LCQMC. Results reveal a significant improvement in performance compared to traditional methods, particularly in terms of accuracy.
%U https://aclanthology.org/2024.lrec-main.1027
%P 11766-11775
Markdown (Informal)
[Multi-Granularity Fusion Text Semantic Matching Based on WoBERT](https://aclanthology.org/2024.lrec-main.1027) (Yu et al., LREC-COLING 2024)
ACL