Joint Learning Templates and Slots for Event Schema Induction
This addresses event schema induction for natural language processing applications, representing an incremental improvement over prior methods.
The paper tackles automatic event schema induction by proposing a joint entity-driven model that simultaneously learns event templates and slots using entity semantic information and normalized cut criteria from image segmentation. The experiment shows the model achieves relatively higher results than previous work.
Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type. In this paper, we propose a joint entity-driven model to learn templates and slots simultaneously based on the constraints of templates and slots in the same sentence. In addition, the entities' semantic information is also considered for the inner connectivity of the entities. We borrow the normalized cut criteria in image segmentation to divide the entities into more accurate template clusters and slot clusters. The experiment shows that our model gains a relatively higher result than previous work.