DS-Group at SIGHAN-2024 dimABSA Task: Constructing In-context Learning Structure for Dimensional Aspect-Based Sentiment Analysis

Ling Ang Meng, Tianyu Zhao, Dawei Song*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Aspect-Based Sentiment Analysis (ABSA) is an important subtask in Natural Language Processing (NLP). More recent research within ABSA have consistently focused on conducting more precise sentiment analysis on aspects, i.e., dimensional Aspect-Based Sentiment Analysis (dimABSA). However, previous approaches have not systematically explored the use of Large Language Models (LLMs) in dimABSA. To fill the gap, we propose a novel In-Context Learning (ICL) structure with a novel aspect-aware ICL example selection method, to enhance the performance of LLMs in dimABSA. Experiments show that our proposed ICL structure significantly improves the fine-grained sentiment analysis abilities of LLMs. Our code is publicly available at: https://github.com/Maydayflower/dimABSA-ICL.

Original languageEnglish
Title of host publicationSIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop
EditorsKam-Fai Wong, Min Zhang, Ruifeng Xu, Jing Li, Zhongyu Wei, Lin Gui, Bin Liang, Runcong Zhao
PublisherAssociation for Computational Linguistics (ACL)
Pages127-132
Number of pages6
ISBN (Electronic)9798891761551
Publication statusPublished - 2024
Event10th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2024 - Bangkok, Thailand
Duration: 16 Aug 2024 → …

Publication series

NameSIGHAN 2024 - 10th SIGHAN Workshop on Chinese Language Processing, Proceedings of the Workshop

Conference

Conference10th SIGHAN Workshop on Chinese Language Processing, SIGHAN 2024
Country/TerritoryThailand
CityBangkok
Period16/08/24 → …

Fingerprint

Dive into the research topics of 'DS-Group at SIGHAN-2024 dimABSA Task: Constructing In-context Learning Structure for Dimensional Aspect-Based Sentiment Analysis'. Together they form a unique fingerprint.

Cite this