Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling
This work addresses the problem of automated creative writing assistance for authors and media applications, but it is incremental as it builds on existing neural methods with specific modifications.
The paper tackled the task of sentence expansion and enhancement for creative writing by implementing a neural expander trained on fiction compressions, showing that the generated expansions are comparable in human preference to original input sentences and outperform baselines.
We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way. The expansion should be understandable, believably grammatical, and optimally meaning-preserving. Sentence expansion and enhancement may serve as an authoring tool, or integrate in dynamic media, conversational agents, or variegated advertising. We implement a neural sentence expander trained on sentence compressions generated from a corpus of modern fiction. We modify an MLE objective to support the task by focusing on new words, and decode at test time with controlled curve-like novelty sampling. We run our sentence expander on sentences provided by human subjects and have humans evaluate these expansions. We show that, although the generation methods are inferior to professional human writers, they are comparable to, and as well liked as, our subjects' original input sentences, and preferred over baselines.