Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu


Abstract
The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the task-specific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.
Anthology ID:
2020.emnlp-main.304
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3722–3732
Language:
URL:
https://aclanthology.org/2020.emnlp-main.304
DOI:
10.18653/v1/2020.emnlp-main.304
Bibkey:
Cite (ACL):
Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, and Xudong Liu. 2020. Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3722–3732, Online. Association for Computational Linguistics.
Cite (Informal):
Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations (Sun et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2020.emnlp-main.304.pdf
Video:
 https://slideslive.com/38939355
Data
WebNLG