Abstract
Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information. However, events in one sentence are usually interdependent and sentence-level information is often insufficient to resolve ambiguities for some types of events. This paper proposes a novel framework dubbed as Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms (HBTNGMA) to solve the two problems simultaneously. Firstly, we propose a hierachical and bias tagging networks to detect multiple events in one sentence collectively. Then, we devise a gated multi-level attention to automatically extract and dynamically fuse the sentence-level and document-level information. The experimental results on the widely used ACE 2005 dataset show that our approach significantly outperforms other state-of-the-art methods.- Anthology ID:
- D18-1158
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1267–1276
- Language:
- URL:
- https://aclanthology.org/D18-1158
- DOI:
- 10.18653/v1/D18-1158
- Cite (ACL):
- Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, and Yantao Jia. 2018. Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1267–1276, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms (Chen et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/D18-1158.pdf
- Code
- yubochen/NBTNGMA4ED