Modeling Complex Event Scenarios via Simple Entity-focused Questions
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 14 Feb 2023.
Builds on
16 of 37 references.
References · 16
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
- 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
- 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
- 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
- 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
- 2019Controlled Crowdsourcing for High-Quality QA-SRL Annotationcited by 34
- 2021ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoningcited by 30
- 2021Asking It All: Generating Contextualized Questions for any Semantic Rolecited by 22
- 2017Event Representations with Tensor-based Compositionscited by 14
4 more
Built on by
Not cited yet.