Abstract
This paper tackles the task of event detection, which involves identifying and categorizing events. The previous work mainly exist two problems: (1) the traditional feature-based methods apply cross-sentence information, yet need taking a large amount of human effort to design complicated feature sets and inference rules; (2) the representation-based methods though overcome the problem of manually extracting features, while just depend on local sentence representation. Considering local sentence context is insufficient to resolve ambiguities in identifying particular event types, therefore, we propose a novel document level Recurrent Neural Networks (DLRNN) model, which can automatically extract cross-sentence clues to improve sentence level event detection without designing complex reasoning rules. Experiment results show that our approach outperforms other state-of-the-art methods on ACE 2005 dataset without external knowledge base.- Anthology ID:
- I17-1036
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 352–361
- Language:
- URL:
- https://aclanthology.org/I17-1036
- DOI:
- Cite (ACL):
- Shaoyang Duan, Ruifang He, and Wenli Zhao. 2017. Exploiting Document Level Information to Improve Event Detection via Recurrent Neural Networks. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 352–361, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Exploiting Document Level Information to Improve Event Detection via Recurrent Neural Networks (Duan et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/I17-1036.pdf