Abstract
Retrospective event detection is an important task for discovering previously unidentified events in a text stream. In this paper, we propose two fast centroid-aware event detection models based on a novel text stream representation – Burst Information Networks (BINets) for addressing the challenge. The BINets are time-aware, efficient and can be easily analyzed for identifying key information (centroids). These advantages allow the BINet-based approaches to achieve the state-of-the-art performance on multiple datasets, demonstrating the efficacy of BINets for the task of event detection.- Anthology ID:
- C16-1309
- Volume:
- Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Yuji Matsumoto, Rashmi Prasad
- Venue:
- COLING
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 3276–3286
- Language:
- URL:
- https://aclanthology.org/C16-1309
- DOI:
- Cite (ACL):
- Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, and Ming Zhou. 2016. Event Detection with Burst Information Networks. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3276–3286, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- Event Detection with Burst Information Networks (Ge et al., COLING 2016)
- PDF:
- https://preview.aclanthology.org/landing_page/C16-1309.pdf