Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction

Oscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, Eneko Agirre


Abstract
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relations produced in less than 15 min per relation. The system relies on a pretrained textual entailment engine which is run as-is (no training examples, zero-shot) or further fine-tuned on labeled examples (few-shot or fully trained). In our experiments on TACRED we attain 63% F1 zero-shot, 69% with 16 examples per relation (17% points better than the best supervised system on the same conditions), and only 4 points short to the state-of-the-art (which uses 20 times more training data). We also show that the performance can be improved significantly with larger entailment models, up to 12 points in zero-shot, allowing to report the best results to date on TACRED when fully trained. The analysis shows that our few-shot systems are specially effective when discriminating between relations, and that the performance difference in low data regimes comes mainly from identifying no-relation cases.
Anthology ID:
2021.emnlp-main.92
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1199–1212
Language:
URL:
https://aclanthology.org/2021.emnlp-main.92
DOI:
10.18653/v1/2021.emnlp-main.92
Bibkey:
Cite (ACL):
Oscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, and Eneko Agirre. 2021. Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1199–1212, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction (Sainz et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.92.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.92.mp4
Code
 osainz59/Ask2Transformers
Data
MultiNLI