@inproceedings{wang-etal-2024-mevtr-multilingual,
title = "{MEVTR}: A Multilingual Model Enhanced with Visual Text Representations",
author = "Wang, Xiaohua and
Fei, Wenlong and
Hu, Min and
Zhang, Qingyu and
Zhu, Aoqiang",
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.983",
pages = "11247--11261",
abstract = "The goal of multilingual modelling is to generate multilingual text representations for various downstream tasks in different languages. However, some state-of-the-art pre-trained multilingual models perform poorly on many low-resource languages due to the lack of representation space and model capacity. To alleviate this issue, we propose a Multilingual model Enhanced with Visual Text Representations (MEVTR), which complements textual representations and extends the multilingual representation space with visual text representations. First, the visual encoder focuses on the glyphs and structure of the text to obtain visual text representations, and the textual encoder obtains textual representations. Then, multilingual representations are enhanced by aligning and fusing visual text representations and textual representations. Moreover, we propose similarity constraint, a self-supervised task to prompt the visual encoder to focus on more additional information. Prefix alignment and multi-head bilinear module are designed to acquire an improved integration effect of visual text representations and textual representations. Experimental results indicate that MEVTR benefits from visual text representations and achieves significant performance gains in downstream tasks. In particular, in the zero-shot cross-lingual transfer task, MEVTR achieves results that outperform the state-of-the-art adapter-based framework without the target language adapter.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-mevtr-multilingual">
<titleInfo>
<title>MEVTR: A Multilingual Model Enhanced with Visual Text Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaohua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlong</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aoqiang</namePart>
<namePart type="family">Zhu</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>The goal of multilingual modelling is to generate multilingual text representations for various downstream tasks in different languages. However, some state-of-the-art pre-trained multilingual models perform poorly on many low-resource languages due to the lack of representation space and model capacity. To alleviate this issue, we propose a Multilingual model Enhanced with Visual Text Representations (MEVTR), which complements textual representations and extends the multilingual representation space with visual text representations. First, the visual encoder focuses on the glyphs and structure of the text to obtain visual text representations, and the textual encoder obtains textual representations. Then, multilingual representations are enhanced by aligning and fusing visual text representations and textual representations. Moreover, we propose similarity constraint, a self-supervised task to prompt the visual encoder to focus on more additional information. Prefix alignment and multi-head bilinear module are designed to acquire an improved integration effect of visual text representations and textual representations. Experimental results indicate that MEVTR benefits from visual text representations and achieves significant performance gains in downstream tasks. In particular, in the zero-shot cross-lingual transfer task, MEVTR achieves results that outperform the state-of-the-art adapter-based framework without the target language adapter.</abstract>
<identifier type="citekey">wang-etal-2024-mevtr-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.983</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11247</start>
<end>11261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEVTR: A Multilingual Model Enhanced with Visual Text Representations
%A Wang, Xiaohua
%A Fei, Wenlong
%A Hu, Min
%A Zhang, Qingyu
%A Zhu, Aoqiang
%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 wang-etal-2024-mevtr-multilingual
%X The goal of multilingual modelling is to generate multilingual text representations for various downstream tasks in different languages. However, some state-of-the-art pre-trained multilingual models perform poorly on many low-resource languages due to the lack of representation space and model capacity. To alleviate this issue, we propose a Multilingual model Enhanced with Visual Text Representations (MEVTR), which complements textual representations and extends the multilingual representation space with visual text representations. First, the visual encoder focuses on the glyphs and structure of the text to obtain visual text representations, and the textual encoder obtains textual representations. Then, multilingual representations are enhanced by aligning and fusing visual text representations and textual representations. Moreover, we propose similarity constraint, a self-supervised task to prompt the visual encoder to focus on more additional information. Prefix alignment and multi-head bilinear module are designed to acquire an improved integration effect of visual text representations and textual representations. Experimental results indicate that MEVTR benefits from visual text representations and achieves significant performance gains in downstream tasks. In particular, in the zero-shot cross-lingual transfer task, MEVTR achieves results that outperform the state-of-the-art adapter-based framework without the target language adapter.
%U https://aclanthology.org/2024.lrec-main.983
%P 11247-11261
Markdown (Informal)
[MEVTR: A Multilingual Model Enhanced with Visual Text Representations](https://aclanthology.org/2024.lrec-main.983) (Wang et al., LREC-COLING 2024)
ACL