End-to-End Coreference Resolution via Hypergraph Partitioning

摘要：

We describe a novel approach to coreference resolution which implements a global decision via hypergraph partitioning. In constrast to almost all previous approaches, we do not rely on separate classification and clustering steps, but perform coreference resolution globally in one step. Our hypergraph-based global model implemented within an endto- end coreference resolution system outperforms two strong baselines (Soon et al., 2001; Bengtson & Roth, 2008) using system mentions only.

作者: Jie Cai Michael Strube

作者单位: Natural Language Processing GroupHeidelberg Institute for Theoretical Studies gGmbH Natural Language Processing Group Heidelberg Institute for Theoretical Studies gGmbH

会议类型: 国际会议

会议名称: The 23rd International Conference on Computational Linguistics(第23届国际计算语言学大会)

会议地点: 北京

会议语种:英文

页码: 143-151

在线出版日期: 2010-08-01（万方平台首次上网日期，不代表论文的发表时间）