Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning Semantic Script Knowledge with Event Embeddings
Ashutosh Modi, ivan titov
Dec 19, 2013 (modified: Dec 19, 2013)ICLR 2014 workshop submissionreaders: everyone
Decision:submitted, no decision
Abstract:Induction of common sense knowledge about prototypical sequences of events has recently received much attention. Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representations of event realizations are computed based on distributed representations of predicates and their arguments, and then these representations are used to predict prototypical event orderings. The parameters of the compositional process for computing the event representations and the ranking component of the model are jointly estimated from unlabeled texts. We show that this approach results in a substantial boost in ordering performance with respect to previous methods.
Enter your feedback below and we'll get back to you as soon as possible.