基于词典的多语种语言模型微调,用于低资源语言情感分析

IF 8.4 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Vinura Dhananjaya, Surangika Ranathunga, Sanath Jayasena
{"title":"基于词典的多语种语言模型微调,用于低资源语言情感分析","authors":"Vinura Dhananjaya,&nbsp;Surangika Ranathunga,&nbsp;Sanath Jayasena","doi":"10.1049/cit2.12333","DOIUrl":null,"url":null,"abstract":"<p>Pre-trained multilingual language models (PMLMs) such as mBERT and XLM-R have shown good cross-lingual transferability. However, they are not specifically trained to capture cross-lingual signals concerning sentiment words. This poses a disadvantage for low-resource languages (LRLs) that are under-represented in these models. To better fine-tune these models for sentiment classification in LRLs, a novel intermediate task fine-tuning (ITFT) technique based on a sentiment lexicon of a high-resource language (HRL) is introduced. The authors experiment with LRLs Sinhala, Tamil and Bengali for a 3-class sentiment classification task and show that this method outperforms vanilla fine-tuning of the PMLM. It also outperforms or is on-par with basic ITFT that relies on an HRL sentiment classification dataset.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 5","pages":"1116-1125"},"PeriodicalIF":8.4000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12333","citationCount":"0","resultStr":"{\"title\":\"Lexicon-based fine-tuning of multilingual language models for low-resource language sentiment analysis\",\"authors\":\"Vinura Dhananjaya,&nbsp;Surangika Ranathunga,&nbsp;Sanath Jayasena\",\"doi\":\"10.1049/cit2.12333\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Pre-trained multilingual language models (PMLMs) such as mBERT and XLM-R have shown good cross-lingual transferability. However, they are not specifically trained to capture cross-lingual signals concerning sentiment words. This poses a disadvantage for low-resource languages (LRLs) that are under-represented in these models. To better fine-tune these models for sentiment classification in LRLs, a novel intermediate task fine-tuning (ITFT) technique based on a sentiment lexicon of a high-resource language (HRL) is introduced. The authors experiment with LRLs Sinhala, Tamil and Bengali for a 3-class sentiment classification task and show that this method outperforms vanilla fine-tuning of the PMLM. It also outperforms or is on-par with basic ITFT that relies on an HRL sentiment classification dataset.</p>\",\"PeriodicalId\":46211,\"journal\":{\"name\":\"CAAI Transactions on Intelligence Technology\",\"volume\":\"9 5\",\"pages\":\"1116-1125\"},\"PeriodicalIF\":8.4000,\"publicationDate\":\"2024-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12333\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"CAAI Transactions on Intelligence Technology\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/cit2.12333\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cit2.12333","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

预先训练的多语言语言模型(PMLM),如 mBERT 和 XLM-R,已经显示出良好的跨语言可移植性。然而,这些模型并没有经过专门训练,无法捕捉有关情感词的跨语言信号。这给低资源语言(LRL)带来了不利因素,因为这些语言在这些模型中的代表性不足。为了更好地针对 LRLs 中的情感分类对这些模型进行微调,介绍了一种基于高资源语言(HRL)情感词典的新型中间任务微调(ITFT)技术。作者用僧伽罗语、泰米尔语和孟加拉语的 LRL 进行了三类情感分类任务的实验,结果表明这种方法优于 PMLM 的香草微调。它还优于依赖于 HRL 情感分类数据集的基本 ITFT,或者与之相当。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Lexicon-based fine-tuning of multilingual language models for low-resource language sentiment analysis

Lexicon-based fine-tuning of multilingual language models for low-resource language sentiment analysis

Pre-trained multilingual language models (PMLMs) such as mBERT and XLM-R have shown good cross-lingual transferability. However, they are not specifically trained to capture cross-lingual signals concerning sentiment words. This poses a disadvantage for low-resource languages (LRLs) that are under-represented in these models. To better fine-tune these models for sentiment classification in LRLs, a novel intermediate task fine-tuning (ITFT) technique based on a sentiment lexicon of a high-resource language (HRL) is introduced. The authors experiment with LRLs Sinhala, Tamil and Bengali for a 3-class sentiment classification task and show that this method outperforms vanilla fine-tuning of the PMLM. It also outperforms or is on-par with basic ITFT that relies on an HRL sentiment classification dataset.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CAAI Transactions on Intelligence Technology
CAAI Transactions on Intelligence Technology COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
11.00
自引率
3.90%
发文量
134
审稿时长
35 weeks
期刊介绍: CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信