基于会话式机器阅读理解模型的事件抽取方法  

Event Extraction Method Based on Conversational Machine Reading Comprehension Model

作　　者：刘露平 周欣 程军军[2] 何小海 卿粼波[1] 王美玲[1] LIU Luping;ZHOU Xin;CHEN Junjun;He Xiaohai;QING Linbo;WANG Meiling(College of Electronics and Information Engineering,Sichuan University,Chengdu 610065,China;China Information Technology Security Evaluation Center,Beijing,100085,China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]中国信息安全测评中心,北京100085

出　　处：《计算机科学》2023年第2期275-284,共10页Computer Science

基　　金：国家自然科学基金(60903098);成都市重大应用示范项目(2019-YF09-00120-SN)。

摘　　要：事件抽取旨在从海量的非结构化文本中自动提取出结构化描述信息,以帮助人们快速地了解事件的最新发展动态。传统的事件抽取方法主要采用分类或者序列标注的方法,其依赖于大量的标注数据来训练模型。近年来,研究者提出了利用机器阅读理解模型来进行事件抽取的方法,通过任务转换并联合利用机器阅读理解任务中的标注数据进行训练来缓解标注数据的不足。然而现有方法局限于单轮问答,问答对之间缺少依赖关系;此外,已有方法也未充分利用句子中的实体信息等知识。针对以上不足,提出了一种会话式机器阅读理解框架用于事件抽取,针对已有方法进行了两方面的扩展:首先,通过在句子中显式地增加实体标记信息,使得模型能够有效地学习到输入句子中的实体知识;其次,设计了历史会话信息编码模块,并结合注意力机制从历史会话中筛选出重要信息,融合到阅读理解模型中以辅助推断。最后,在公开数据集上的实验结果表明所提模型相比已有方法取得了更优的结果。Event extraction aims to extract structured information automatically from massive unstructured texts to help people quickly understand the latest developments of events.Traditional methods are mainly implemented by classification or sequence labeling methods,which rely on a large amount of labeled data to train the model.In recent years,researchers have proposed to use machine reading comprehension models for event extraction,and through task conversion and combined use of machine rea-ding comprehension datasets for training to effectively alleviate the issue of insufficient annotation data.However,existing methods are limited to a single round of question answering and lack dependencies between different question and answer rounds.In addition,existing methods do not fully utilize entity knowledge in sentences.To this end,a new machine reading comprehension model for event extraction is proposed,and we extend existing methods in two ways.Firstly,by explicitly adding entity tag information in the sentence,making the model effectively learn the prior knowledge of the entities in the input sentence.Secondly,a historical conversational information encoding module is designed,and the attention mechanism is utilized to select important information from historical conversations to assist in inference.Finally,experiment results on a public dataset show that the new model achieves better performance than the existing methods based on the machine reading comprehension model.

关 键 词：事件抽取 会话式机器阅读理解 实体信息标记 历史会话信息编码 注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]