面向多语料库的通用事件指代消解

Towards General Event Coreference Resolution for Multiple Corpora

事件同指消解对篇章理解、信息抽取意义重大。该文在事件抽取完成的基础上聚焦事件同指,给出了一个基于卷积神经网络的事件同指消解完整框架,针对实例分布不均衡问题给出了基于事件语义类别和时态信息的事件兼容性过滤策略。为了最大化适用不同的事件标注策略,提出了最小事件本身描述和事件间关系描述相结合的特征表示方法。针对基于事件对模型进行同指消解产生的局部最优问题,给出了一种全局优化的后处理方案。在KBP2015和ACE2005语料上的各类实验表明,上述三个解决方案均能有效解决问题,提升整个事件同指消解平台的性能。

Event co-reference resolution has obvious impact on many other NLP applications,i.e.,discourse analysis,information extraction,and so on.A complete framework based on CNNs is proposed for event coreference resolution.Three issues are addressed.First,filtering strategies from the perspective of semantic compatibility and temporal consistency are employed to reduce the distribution imbalance.Second,the combination representation of minimum event self-description and additional relationship description between events is applied for different event annotation schemas,i.e.,multiple corpora.Finally,aglobal inference post-processing is designed to optimize the local optimal solution generated by event-pair model.Experiments on KPB2015 and ACE2005 corpora show the effectiveness of our proposed approach.