@inproceedings{kayal-etal-2024-jlbert-japanese,
title = "{JLB}ert: {J}apanese Light {BERT} for Cross-Domain Short Text Classification",
author = "Kayal, Chandrai and
Chattopadhyay, Sayantan and
Gupta, Aryan and
Abrol, Satyen and
Gugol, Archie",
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.833",
pages = "9536--9542",
abstract = "Models, such as BERT, have made a significant breakthrough in the Natural Language Processing (NLP) domain solving 11+ tasks. This is achieved by training on a large scale of unlabelled text resources and leveraging Transformers architecture making it the {``}Jack of all NLP trades{''}. However, one of the popular and challenging tasks in Sequence Classification is Short Text Classification (STC). Short Texts face the problem of being short, equivocal, and non-standard. In this paper, we address two major problems: 1. Improving STC tasks performance in Japanese language which consists of many varieties and dialects. 2. Building a light-weight Japanese BERT model with cross-domain functionality and comparable accuracy with State of the Art (SOTA) BERT models. To solve this, we propose a novel cross-domain scalable model called JLBert, which is pre-trained on a rich, diverse and less explored Japanese e-commerce corpus. We present results from extensive experiments to show that JLBert is outperforming SOTA Multilingual and Japanese specialized BERT models on three Short Text datasets by approx 1.5{\%} across various domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kayal-etal-2024-jlbert-japanese">
<titleInfo>
<title>JLBert: Japanese Light BERT for Cross-Domain Short Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chandrai</namePart>
<namePart type="family">Kayal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sayantan</namePart>
<namePart type="family">Chattopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aryan</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satyen</namePart>
<namePart type="family">Abrol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Archie</namePart>
<namePart type="family">Gugol</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>Models, such as BERT, have made a significant breakthrough in the Natural Language Processing (NLP) domain solving 11+ tasks. This is achieved by training on a large scale of unlabelled text resources and leveraging Transformers architecture making it the “Jack of all NLP trades”. However, one of the popular and challenging tasks in Sequence Classification is Short Text Classification (STC). Short Texts face the problem of being short, equivocal, and non-standard. In this paper, we address two major problems: 1. Improving STC tasks performance in Japanese language which consists of many varieties and dialects. 2. Building a light-weight Japanese BERT model with cross-domain functionality and comparable accuracy with State of the Art (SOTA) BERT models. To solve this, we propose a novel cross-domain scalable model called JLBert, which is pre-trained on a rich, diverse and less explored Japanese e-commerce corpus. We present results from extensive experiments to show that JLBert is outperforming SOTA Multilingual and Japanese specialized BERT models on three Short Text datasets by approx 1.5% across various domain.</abstract>
<identifier type="citekey">kayal-etal-2024-jlbert-japanese</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.833</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9536</start>
<end>9542</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JLBert: Japanese Light BERT for Cross-Domain Short Text Classification
%A Kayal, Chandrai
%A Chattopadhyay, Sayantan
%A Gupta, Aryan
%A Abrol, Satyen
%A Gugol, Archie
%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 kayal-etal-2024-jlbert-japanese
%X Models, such as BERT, have made a significant breakthrough in the Natural Language Processing (NLP) domain solving 11+ tasks. This is achieved by training on a large scale of unlabelled text resources and leveraging Transformers architecture making it the “Jack of all NLP trades”. However, one of the popular and challenging tasks in Sequence Classification is Short Text Classification (STC). Short Texts face the problem of being short, equivocal, and non-standard. In this paper, we address two major problems: 1. Improving STC tasks performance in Japanese language which consists of many varieties and dialects. 2. Building a light-weight Japanese BERT model with cross-domain functionality and comparable accuracy with State of the Art (SOTA) BERT models. To solve this, we propose a novel cross-domain scalable model called JLBert, which is pre-trained on a rich, diverse and less explored Japanese e-commerce corpus. We present results from extensive experiments to show that JLBert is outperforming SOTA Multilingual and Japanese specialized BERT models on three Short Text datasets by approx 1.5% across various domain.
%U https://aclanthology.org/2024.lrec-main.833
%P 9536-9542
Markdown (Informal)
[JLBert: Japanese Light BERT for Cross-Domain Short Text Classification](https://aclanthology.org/2024.lrec-main.833) (Kayal et al., LREC-COLING 2024)
ACL
- Chandrai Kayal, Sayantan Chattopadhyay, Aryan Gupta, Satyen Abrol, and Archie Gugol. 2024. JLBert: Japanese Light BERT for Cross-Domain Short Text Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9536–9542, Torino, Italia. ELRA and ICCL.