Abstract
We introduce GenDecider, a novel re-ranking approach for Zero-Shot Entity Linking (ZSEL), built on the Llama model. It innovatively detects scenarios where the correct entity is not among the retrieved candidates, a common oversight in existing re-ranking methods. By autoregressively generating outputs based on the context of the entity mention and the candidate entities, GenDecider significantly enhances disambiguation, improving the accuracy and reliability of ZSEL systems, as demonstrated on the benchmark ZESHEL dataset. Our code is available at https://github.com/kangISU/GenDecider.- Anthology ID:
- 2024.naacl-short.22
- Volume:
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 239–245
- Language:
- URL:
- https://aclanthology.org/2024.naacl-short.22
- DOI:
- 10.18653/v1/2024.naacl-short.22
- Cite (ACL):
- Kang Zhou, Yuepei Li, Qing Wang, Qiao Qiao, and Qi Li. 2024. GenDecider: Integrating “None of the Candidates” Judgments in Zero-Shot Entity Linking Re-ranking. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 239–245, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- GenDecider: Integrating “None of the Candidates” Judgments in Zero-Shot Entity Linking Re-ranking (Zhou et al., NAACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.naacl-short.22.pdf