Abstract
This paper exploits a sentiment extractor supported by syntactic and lexical resources to enhance multilingual sentiment classification solved through the generative approach, without retraining LLMs. By adding external information of words and phrases that have positive/negative polarities, the multilingual sentiment classification error was reduced by up to 33 points, and the combination of two approaches performed best especially in high-performing pairs of LLMs and languages.- Anthology ID:
- 2024.findings-acl.286
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4810–4817
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.286
- DOI:
- 10.18653/v1/2024.findings-acl.286
- Cite (ACL):
- Hiroshi Kanayama, Yang Zhao, Ran Iwamoto, and Takuya Ohko. 2024. Incorporating Syntax and Lexical Knowledge to Multilingual Sentiment Classification on Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4810–4817, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Incorporating Syntax and Lexical Knowledge to Multilingual Sentiment Classification on Large Language Models (Kanayama et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/autopr/2024.findings-acl.286.pdf