"What Are You Trying to Do?" Semantic Typing of Event Processes
This work addresses a cognitively motivated semantic typing problem for natural language processing, with incremental contributions in dataset creation and method adaptation.
The paper tackles the task of multi-axis event process typing, which infers free-form labels for action and object types in event processes, by developing a dataset of over 60k processes and proposing the P2GT hybrid learning framework. The result shows that P2GT effectively identifies process intents and object types, with capabilities for few-shot cases and strong generalizability to out-of-domain processes.
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action made by the process and (ii) the type of object the process seeks to affect. This task is inspired by computational and cognitive studies of event understanding, which suggest that understanding processes of events is often directed by recognizing the goals, plans or intentions of the protagonist(s). We develop a large dataset containing over 60k event processes, featuring ultra fine-grained typing on both the action and object type axes with very large ($10^3\sim 10^4$) label vocabularies. We then propose a hybrid learning framework, P2GT, which addresses the challenging typing problem with indirect supervision from glosses1and a joint learning-to-rank framework. As our experiments indicate, P2GT supports identifying the intent of processes, as well as the fine semantic type of the affected object. It also demonstrates the capability of handling few-shot cases, and strong generalizability on out-of-domain event processes.