Abstract: The autors propose an event relation recognition method based on event inference cues by analyzing the semantic dependency relation and event arguments distribution features between events and the rules of event inference. Experiment result shows that the proposed method achieves 9.57% improvement compared with the traditional method based on event term and entity.

Key words: inference cue, dependency cue, event term, event entity, event relation

摘要： 利用同一话题下的事件元素在话题内的分布特性以及事件元素在话题演化过程中的语义依存规律, 提出基于推理线索构建的事件关系识别方法。实验结果显示, 相比于基于核心词和实体推理的事件关系识别方法, 所提出的方法在F值上获得9.57%的性能提升。

关键词: 推理线索, 依存线索, 事件核心词, 事件元素, 事件关系