Event Representations with Tensor-based Compositions
This work addresses the problem of robust event representation for language understanding, offering incremental improvements in capturing semantic interactions.
The authors tackled the challenge of creating effective event representations for script-like sequences by proposing a tensor-based composition method, which improved performance on multiple event-related tasks and generated better schemas compared to prior discrete methods.
Robust and flexible event representations are important to many core areas in language understanding. Scripts were proposed early on as a way of representing sequences of events for such understanding, and has recently attracted renewed attention. However, obtaining effective representations for modeling script-like event sequences is challenging. It requires representations that can capture event-level and scenario-level semantics. We propose a new tensor-based composition method for creating event representations. The method captures more subtle semantic interactions between an event and its entities and yields representations that are effective at multiple event-related tasks. With the continuous representations, we also devise a simple schema generation method which produces better schemas compared to a prior discrete representation based method. Our analysis shows that the tensors capture distinct usages of a predicate even when there are only subtle differences in their surface realizations.