Information-based Event Coreference

Event Coreference;Easy-First Clustering;Event Argument

Wang, Ruichen ; Roth ; Dan

关键词: Event Coreference;    Easy-First Clustering;    Event Argument;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/89094/WANG-THESIS-2015.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Event Coreference is an important module in the event extraction task, which hasbeen shown to be difficult to solve. The goal is to link mentions talking aboutthe same event together so that the information could be aggregated. This taskcould further be split into two slightly different subtasks: Within-Doc EventCoreference and Cross-Doc Event Coreference. Most of the related publicationstried to solve the problem of Event Coreference in a two-step manner: Train ordesign a similarity metric for event mention pairs, then apply some clusteringalgorithm to the event mention space using the similarity metric as distance. In this work, we identify two major problems people have neglected: One is thatcoreference does not imply full event mention similarity due to the fact thatevent mentions tend to contain partial and even complementary information. Theother problem is that the order to compare event mentions pair could be important, because instead of comparing event mentions pairs that have incomplete andtrustless information, comparing those who have complete and trustworthyinformation first could prune the error rate. We propose Core Similarity, a newargument-based similarity metric, to solve the first problem, and twoinformation-based clustering algorithms for the second problem -Informative-First Clustering (IFC) for within-doc situation and Topic-Side EventClustering (TSEC) for cross-doc situation. These clustering algorithms are basedon the idea of Event Information which is defined in this work. Finally, theEVCO system is delivered with all of these details implemented.