Description Boosting for Zero-Shot Entity and Relation Classification

Gabriele Picco, Leopold Fuchs, Marcos Martínez Galindo, Alberto Purpura, Vanessa López, Hoang Thanh Lam

Abstract
Zero-shot entity and relation classification models leverage available external information of unseen classes – e.g., textual descriptions – to annotate input text data. Thanks to the minimum data requirement, Zero-Shot Learning (ZSL) methods have high value in practice, especially in applications where labeled data is scarce. Even though recent research in ZSL has demonstrated significant results, our analysis reveals that those methods are sensitive to provided textual descriptions of entities (or relations). Even a minor modification of descriptions can lead to a change in the decision boundary between entity (or relation) classes. In this paper, we formally define the problem of identifying effective descriptions for zero shot inference. We propose a strategy for generating variations of an initial description, a heuristic for ranking them and an ensemble method capable of boosting the predictions of zero-shot models through description enhancement. Empirical results on four different entity and relation classification datasets show that our proposed method outperform existing approaches and achieve new SOTA results on these datasets under the ZSL settings. The source code of the proposed solutions and the evaluation framework are open-sourced.
Anthology ID:
2024.findings-acl.562
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9441–9457
Language:
URL:
https://aclanthology.org/2024.findings-acl.562
DOI:
10.18653/v1/2024.findings-acl.562
Bibkey:
Cite (ACL):
Gabriele Picco, Leopold Fuchs, Marcos Martínez Galindo, Alberto Purpura, Vanessa López, and Hoang Thanh Lam. 2024. Description Boosting for Zero-Shot Entity and Relation Classification. In Findings of the Association for Computational Linguistics ACL 2024, pages 9441–9457, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Description Boosting for Zero-Shot Entity and Relation Classification (Picco et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.562.pdf
PDF Search