Abstract
Natural language text contains numerous event-based, and a large number of semantic relations exist between events. Event relations express the event rationality logic and reveal the evolution process of events, which is of great significance for machines to understand the text and the construction of event-based knowledge base. Event relation discovery includes extracting event relation from text and obtaining event relation by reasoning. Event relation extraction focuses on the recognition of explicit relations, while event relation reasoning can also discover implicit relations, which is more meaningful and more difficult. In this paper, we propose a model combining LSTM and attention mechanism for event relation reasoning, which uses the attention mechanism to dynamically generate event sequence representation according to the type of relation and predicts the event relation. The macro-F1 value in the experimental result reaches 63.71%, which shows that the model can effectively discover implicit event-event relation.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
