Abstract
An Event, containing a sequence of subevents, describes a typical thing that happens at a specific time and place. Predicting next probable subevents based on knowledge acquired from large-scale news documents are very important for many real-world applications, such as disaster warning etc. In this paper, we present a novel hierarchical attention based end-to-end model for future (unknown) subevent prediction using large-scale historical events. Our model automatically produces a short text which describes a possible future subevent after consuming the texts describing previous subevents. To boost the model's understanding towards subevent sequence, we design a hierarchical LSTM model to compress the knowledge in both the word sequence for a subevent and the subevent sequence for an event. In addition, topic information has been exploited to make context-aware prediction for future subevents. To further consider which subevents and words play a critical role in prediction, we propose a hierarchical attention mechanism to stress on the important previous subevents as well as the the critical words within them. Experimental results on a real-world dataset demonstrate the superiority of our model for future subevent prediction over state-of-the-art methods.
Highlights
An Event, which describes a specific thing happened at a specific time and place, always consists of a sequence of subevents recording how things developed in detail
How can we jointly model both the semantic meanings and topic information i.e. context-aware features within an event? Last, different subevents and words may have different importance for future subevent prediction, how can we pay attention to the previous subevents and words which play a key role in predicting the future subevent?
2) We present a hierarchical attention based neural model CH-Long Short-Term Memory (LSTM)-Att, which captures the two-level sequential structures of subevent sequences, and considers different importance of previous subevents and words within the subevents for future subevent prediction
Summary
An Event, which describes a specific thing happened at a specific time and place, always consists of a sequence of subevents recording how things developed in detail. Taking the event ‘‘Egyptian revolution of 2011’’ as an example, given its sequential subevents described by the headlines of news documents,1 ‘‘Conflict occurred again in Egypt on 22nd, and people plan to hold a million-people march’’, and ‘‘Egypt’s military will deliver a speech to respond to the conflict between demonstrators and police’’, our model generates ‘‘protests’’, ‘‘burst’’, ‘‘chaos’’, ‘‘cause’’, ‘‘deaths’’, ‘‘injuries’’ word by word, which constitutes a possible future subevent. It matches well with a later news report ‘‘The Egyptian protest has caused 32 people dead and more than
Sign-in/Register to view highlights & summary 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.
