事件要素注意力与编码层融合的触发词抽取研究

Research on Trigger Word Extraction Based on the Fusion of Event Argument Attention and Encoder Layer

事件抽取是信息抽取的主要任务之一,而触发词抽取是事件抽取的重要子任务.事件要素与事件触发词之间存在关联信息,现有的事件触发词抽取方法主要关注事件触发词本身,没有充分的利用事件要素信息.因此,提出一种事件要素注意力与编码层融合的事件触发词抽取模型,能够有效地利用事件要素信息,提高触发词抽取性能.通过事件要素与事件触发词之间的相关性来显示利用事件要素信息,同时利用编码层的多头自注意力机制间接学习事件要素与事件触发词之间的依赖关系,并将两个方法得到的输出向量进行处理,作为特征送入到编码层中进行训练.此外,通过词特征模型获取语义信息.该方法在ACE2005英文语料上对事件触发词抽取的F值达到71.95%.

Event extraction is one of the main tasks of information extraction,and trigger extraction is an important sub task of event extraction.There is correlation information between event argument and event trigger word,but the existing methods mainly focus on the event trigger word itself and do not make full use of the event argument information.In order to effectively utilize the event argument,this paper proposes an event trigger word extraction model based on the fusion of event argument attention and Encoder layer.First,the correlation between event argument and event trigger word is calculated to display use the event argument information.Then,the relationship between event argument and event trigger words is indirectly learned through the multi-head self-attention mechanism of encoder layer.The output vectors obtained by the two methods are processed and sent into the encoder layer as features for training.In addition,the word feature model can get more abundant semantic information.The experimental results show that the F value of event trigger words extracted from ACE2005 English corpus is up to 71.95%.