Abstains from Prediction: Towards Robust Relation Extraction in Real World

Zhao Jun, Zhang Yongxin, Xu Nuo, Gui Tao, Zhang Qi, Chen Yunwen, Gao Xiang


Abstract
“Supervised learning is a classic paradigm of relation extraction (RE). However, a well-performing model can still confidently make arbitrarily wrong predictions when exposed to samples of unseen relations. In this work, we propose a relation extraction method with rejection option to improve robustness to unseen relations. To enable the classifier to reject unseen relations, we introduce contrastive learning techniques and carefully design a set of class-preserving transformations to improve the discriminability between known and unseen relations. Based on the learned representation, inputs of unseen relations are assigned a low confidence score and rejected. Off-the-shelf open relation extraction (OpenRE) methods can be adopted to discover the potential relations in these rejected inputs. In addition, we find that the rejection can be further improved via readily available distantly supervised data. Experiments on two public datasets prove the effectiveness of our method capturing discriminative representations for unseen relation rejection.”
Anthology ID:
2022.ccl-1.71
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
798–810
Language:
English
URL:
https://aclanthology.org/2022.ccl-1.71
DOI:
Bibkey:
Cite (ACL):
Zhao Jun, Zhang Yongxin, Xu Nuo, Gui Tao, Zhang Qi, Chen Yunwen, and Gao Xiang. 2022. Abstains from Prediction: Towards Robust Relation Extraction in Real World. In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 798–810, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
Abstains from Prediction: Towards Robust Relation Extraction in Real World (Jun et al., CCL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ccl-1.71.pdf
Data
FewRelTACRED