工程科学与技术2024，Vol.56Issue(1)：82-88,7.DOI:10.15961/j.jsuese.202201096
一种端到端的事件共指消解方法
An End-to-end Event Coreference Resolution Method
摘要
Abstract
The event coreference resolution(ECR)is mainly to determine whether different event mentions refer to the same event.ECR not only effectively alleviates the problem of information redundancy in event extraction tasks,but also provides an effective way for event completion.Although many scholars have conducted extensive research on ECR using deep learning methods and achieved significant achievements,there are still issues in most ECR models,such as insufficient explicit information representation,noise introduced by arguments,and sparse distribution of coreference events.Aiming at the above problems,an end-to-end ECR method using explicit argument information and event chain reconstruc-tion was proposed.First,an event extraction model called OneIE was used to extract event triggers and arguments.Then,a Transformer encoder is used to express the context of the event mentions,and the confidence score was introduced into the argument information coding to mitigate the error transmission.Meanwhile,the information of the argument in the horizontal and vertical directions of the trigger was decomposed by the gat-ing mechanism,and the noise of the argument was filtered by fusing the information of the directions according to the correlation coefficient of the argument and the trigger.Afterwards,the coreference score of the event pairs was calculated by the feed forward network.Finally,to verify the validity of the event mentions,the event chains were reconstructed to correct the deviation of the model caused by the sparse event corefer-ence.In order to verify the effectiveness of our method,the proposed model is trained and tested on the public dataset ACE2005.The experiment-al results showed that our model in end-to-end ECR task is 5.67%and 6.24%higher than the other models in the scores of CoNLL and AVG on average.关键词
事件共指消解/自然语言处理/预训练语言模型Key words
event coreference resolution/NLP/pre-trained language model分类
信息技术与安全科学引用本文复制引用
刘浏,蒋国权,环志刚,刘姗姗,刘茗,丁鲲..一种端到端的事件共指消解方法[J].工程科学与技术,2024,56(1):82-88,7.基金项目
国家自然科学基金项目(71901215) （71901215）
江苏省"333工程"培养资金资助项目(BRA2020418) （BRA2020418）
中国博士后科学基金资助项目(2021MD703983) （2021MD703983）
国防科技大学科研计划项目(ZK20-46) （ZK20-46）
宿迁市科技计划项目(K202128) （K202128）
