基于单句表示的篇章事件可信度识别方法

An Approach to Document-Level Event Factuality Identification Based on Sentence-Level Representations

事件可信度表示文本中事件的真实状况,描述了事件是否是一个事实,或是一种可能还是不可能的情形,是自然语言处理中一个重要的语义任务。目前,大多数关于事件可信度分析的方法都集中在句子级,很少涉及篇章级。该文基于卷积神经网络,结合篇章中的句子级特征(包括句子的语义、语法以及线索词特征表示),使用对抗训练来识别篇章可信度。在中英文数据集上的结果显示,该文方法与最新的实验结果相比,微平均F1值分别提高了3.51%和6.02%,宏平均F1值分别提升了4.63%和9.97%。同时,该方法在训练速度上也提高了4倍。

Event factuality denotes the factual nature of events in texts,indicating whether an event is a fact,a possibility,or an impossible situation.As an important semantic task in natural language processing,the existing studies on event factuality identification are focused on sentences-level.Based on the convolutional neural network,this paper proposes document-level factuality by introducting the sentence-level features in the text,including the semantic,grammar and clues of the sentence.Experimental results on both the Chinese and English corpus show that,1)the micro-average F1 is increased by 3.51%and 6.02%,respectively;2)the macro-average F1 is increased by 4.63%and 9.97%,respectively.The training speed of this method is also four times faster than the baseline.