Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates

Mahdi Rahimi, Mihai Surdeanu


Abstract
While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-shot methods have been proposed that reformulate RC into other NLP tasks for which supervision exists such as textual entailment. However, these methods rely on templates that are manually created which is costly and requires domain expertise. In this paper, we present a novel strategy for template generation for relation classification, which is based on adapting Harris’ distributional similarity principle to templates encoded using contextualized representations. Further, we perform empirical evaluation of different strategies for combining the automatically acquired templates with manual templates. The experimental results on TACRED show that our approach not only performs better than the zero-shot RC methods that only use manual templates, but also that it achieves state-of-the-art performance for zero-shot TACRED at 64.3 F1 score.
Anthology ID:
2023.repl4nlp-1.16
Volume:
Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
Venue:
RepL4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
187–195
Language:
URL:
https://aclanthology.org/2023.repl4nlp-1.16
DOI:
10.18653/v1/2023.repl4nlp-1.16
Bibkey:
Cite (ACL):
Mahdi Rahimi and Mihai Surdeanu. 2023. Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates. In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 187–195, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates (Rahimi & Surdeanu, RepL4NLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.repl4nlp-1.16.pdf