Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2016, Vol. 52 ›› Issue (1): 97-103.DOI: 10.13209/j.0479-8023.2016.010

Previous Articles     Next Articles

Global Inference for Co-reference Resolution between Chinese Events

TENG Jiayue, LI Peifeng, ZHU Qiaoming   

  1. School of Computer Science & Technology, Soochow University, Suzhou, 215006
  • Received:2015-06-06 Online:2016-01-20 Published:2016-01-20
  • Contact: LI Peifeng, E-mail: pfli(at)


滕佳月, 李培峰, 朱巧明   

  1. 苏州大学计算机科学与技术学院, 苏州 215006
  • 通讯作者: 李培峰, E-mail: pfli(at)
  • 基金资助:
    国家自然科学基金(61472265, 61331011)和江苏省前瞻性联合研究项目(BY-2014059-08)资助


Currently, most pairwise resolution models for event co-reference focused on classification or clustering approaches, which ignored the relations between events in a document. A global optimization model for event co-reference resolution was proposed to resolve the inconsistent event chains in classifier-based approaches. This model regarded co-reference resolution as a integer linear program problem and introduced various kinds of constraints, such as symmetry, transitivity, triggers, argument roles, event distances, to further improve the performance. The experimental results show that the proposed model outperforms the local classifier by 4.20% in F1-measure.

Key words: Key words event, co-reference relation, global optimization, inference


针对目前对事件同指关系的研究中多采用事件对分类或聚类方法而忽略事件相互之间内在联系的问题, 提出一个中文事件同指消解的全局优化模型, 用于减少因分类器错误造成的同指事件链不一致问题。该模型利用对称性、传递性、触发词、论元角色、事件距离等多种约束条件, 将同指消解转化成整数线性规划问题。实验结果表明, 与分类器方法相比, 全局优化模型的F1值提高4.20%。

关键词: 事件, 同指关系, 全局优化, 推理

CLC Number: