Weakly Supervised Attention Networks for Entity Recognition

Barun Patra, Joel Ruben Antony Moniz


Abstract
The task of entity recognition has traditionally been modelled as a sequence labelling task. However, this usually requires a large amount of fine-grained data annotated at the token level, which in turn can be expensive and cumbersome to obtain. In this work, we aim to circumvent this requirement of word-level annotated data. To achieve this, we propose a novel architecture for entity recognition from a corpus containing weak binary presence/absence labels, which are relatively easier to obtain. We show that our proposed weakly supervised model, trained solely on a multi-label classification task, performs reasonably well on the task of entity recognition, despite not having access to any token-level ground truth data.
Anthology ID:
D19-1652
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6268–6273
Language:
URL:
https://aclanthology.org/D19-1652
DOI:
10.18653/v1/D19-1652
Bibkey:
Cite (ACL):
Barun Patra and Joel Ruben Antony Moniz. 2019. Weakly Supervised Attention Networks for Entity Recognition. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6268–6273, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Weakly Supervised Attention Networks for Entity Recognition (Patra & Moniz, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1652.pdf
Attachment:
 D19-1652.Attachment.pdf