Learning Semantic Script Knowledge with Event Embeddings
This work addresses the challenge of learning semantic script knowledge from text, which is important for natural language understanding tasks, but it appears incremental as it builds on prior graph-based approaches.
The paper tackled the problem of inducing common sense knowledge about prototypical event sequences by using distributed representations of events to predict orderings, resulting in a substantial boost in performance compared to previous methods.
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 texts. We show that this approach results in a substantial boost in ordering performance with respect to previous methods.