M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis

doi:arXiv:2502.11824

	M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis
	Wu, Chengyan 1; Ma, Bolei 2,3; Liu, Yihong 2,3; Zhang, Zheyu 4; Deng, Ningyuan 5; Li, Yanshu 6; Chen, Baolan7 ; Zhang, Yi 8; Plank, Barbara 2,3; Xue, Yun 1
	2025-02-17
状态	已发表
摘要	Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. However, existing ABSA datasets are predominantly English-centric, limiting the scope for multilingual evaluation and research. To bridge this gap, we present M-ABSA, a comprehensive dataset spanning 7 domains and 21 languages, making it the most extensive multilingual parallel dataset for ABSA to date. Our primary focus is on triplet extraction, which involves identifying aspect terms, aspect categories, and sentiment polarities. The dataset is constructed through an automatic translation process with human review to ensure quality. We perform extensive experiments using various baselines to assess performance and compatibility on M-ABSA. Our empirical findings highlight that the dataset enables diverse evaluation tasks, such as multilingual and multi-domain transfer learning, and large language model evaluation, underscoring its inclusivity and its potential to drive advancements in multilingual ABSA research.
语种	英语
DOI	arXiv:2502.11824
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:121697529
WOS类目	Computer Science, Interdisciplinary Applications
资助项目	ERC Consolidator Grant DIALECT[101043235] ; Characteristic Innovation Projects of Guangdong Colleges and Universities[2018KTSCX049] ; National Natural Science Foundation of China[32371114] ; Guangdong Basic and Applied Basic Research Foundation[2023A1515011370]
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/514097
专题	信息科学与技术学院_硕士生
通讯作者	Xue, Yun
作者单位	1.South China Normal Univ, Sch Elect Sci & Engn, Sch Microelect, Guangdong Prov Key Lab Quantum Engn & Quantum Mat, Guangzhou, Peoples R China 2.LMU Munich, Munich, Germany 3.Munich Ctr Machine Learning, Munich, Germany 4.Tech Univ Munich, Munich, Germany 5.Renmin Univ China, Beijing, Peoples R China 6.Brown Univ, Providence, RI 02912, USA 7.ShanghaiTech Univ, Shanghai, Peoples R China 8.Univ Erlangen Nuremberg, Erlangen, Germany
推荐引用方式 GB/T 7714	Wu, Chengyan,Ma, Bolei,Liu, Yihong,et al. M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis. 2025.