Abstract
Zero-shot text classification involves categorizing text into classes without labeled data, typically using a pre-trained language model to compute the correlation between text and class names. This makes it essential for class names to contain sufficient information. Existing methods incorporate semantically similar keywords related to class names, but the properties of effective keywords remain unclear. We demonstrate that effective keywords should possess three properties: 1) keyword relevance to the task objective, 2) inter-class exclusivity, and 3) intra-class diversity. We also propose an automatic method for acquiring keywords that satisfy these properties without additional knowledge bases or data. Experiments on nine real-world datasets show our method outperforms existing approaches in fully zero-shot and generalized zero-shot settings. Ablation studies further confirm the importance of all three properties for superior performance.- Anthology ID:
- 2024.starsem-1.9
- Volume:
- Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Danushka Bollegala, Vered Shwartz
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 106–119
- Language:
- URL:
- https://aclanthology.org/2024.starsem-1.9
- DOI:
- Cite (ACL):
- Taro Yano, Kunihiro Takeoka, and Masafumi Oyamada. 2024. Relevance, Diversity, and Exclusivity: Designing Keyword-augmentation Strategy for Zero-shot Classifiers. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 106–119, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Relevance, Diversity, and Exclusivity: Designing Keyword-augmentation Strategy for Zero-shot Classifiers (Yano et al., *SEM 2024)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/2024.starsem-1.9.pdf