摘要
已有事件间时序关系识别只考虑两个事件所在上下文的局部信息,忽略事件间篇章视角的关联关系.针对这一问题,文中给出融合句子级依存关系和篇章层修辞关系的事件时序关系识别方法.将事件间关联关系分两部分进行表征:事件所在句子的依存路径信息和事件所在基本篇章单元间的修辞关系信息.基于这一表征体系构建可以捕获更多有效信息的神经网络模型,提高事件时序关系识别的性能.在TimeBank-Dense语料上的一系列实验验证文中方法的优越性.
In the identification of temporal relation between the existing events,only the local context of two events is taken into account and the relationship between the events from the perspective of discourse is neglected.To address this issue,a method to identify the temporal relation of events is proposed by combining the discourse rhetoric relation and intra-sentential dependency relation.The inter-event correlation is represented from two aspects,the shortest dependency path between events and the rhetorical relationship between the elementary discourse units of the events location.Based on this representation system,a neural network model is built to capture more effective information and improve the performance of event temporal relation identification.A series of experiments on Timebank-Dense corpus show the superiority of the proposed method.
作者
戴倩雯
张龙印
孔芳
DAI Qianwen;ZHANG Longyin;KONG Fang(Natural Language Processing Laboratory,School of Computer Science and Technology,Soochow University,Suzhou 215006)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2019年第12期1100-1106,共7页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金重点项目(No.61836007)、国家自然科学基金项目(No.61876118)资助~~
关键词
时序关系
依存关系
篇章修辞关系
Temporal Relation
Dependency Relation
Textual Rhetoric Relation