Generating Diverse Story Continuations with Controllable Semantics
This work addresses the need for controllable and diverse text generation in creative writing systems, offering incremental improvements over existing methods.
The authors tackled the problem of generating diverse story continuations with controllable semantics, achieving accurate control over sentence attributes and improved diversity and quality compared to standard beam search, with semantic frames yielding the best results.
We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider several sentence attributes, including sentiment, length, predicates, frames, and automatically-induced clusters. Our empirical results demonstrate: (1) our framework is accurate in terms of generating outputs that match the target control values; (2) our model yields increased maximum metric scores compared to standard n-best list generation via beam search; (3) controlling generation with semantic frames leads to a stronger combination of diversity and quality than other control variables as measured by automatic metrics. We also conduct a human evaluation to assess the utility of providing multiple suggestions for creative writing, demonstrating promising results for the potential of controllable, diverse generation in a collaborative writing system.