Modeling Complex Event Scenarios via Simple Entity-focused Questions
This work addresses the problem of exploring complex event scenarios for natural language processing and interactive applications, representing an incremental improvement over standard event language modeling.
The paper tackles the challenge of modeling complex event scenarios with multiple sequences and participants by proposing a question-guided generation framework that generates events as answers to participant-focused questions, resulting in better participant coverage, diverse events, comparable perplexities, and more effective control for interactive schema generation.
Event scenarios are often complex and involve multiple event sequences connected through different entity participants. Exploring such complex scenarios requires an ability to branch through different sequences, something that is difficult to achieve with standard event language modeling. To address this, we propose a question-guided generation framework that models events in complex scenarios as answers to questions about participants. At any step in the generation process, the framework uses the previously generated events as context, but generates the next event as an answer to one of three questions: what else a participant did, what else happened to a participant, or what else happened. The participants and the questions themselves can be sampled or be provided as input from a user, allowing for controllable exploration. Our empirical evaluation shows that this question-guided generation provides better coverage of participants, diverse events within a domain, comparable perplexities for modeling event sequences, and more effective control for interactive schema generation.