Fiction Sentence Expansion and Enhancement via Focused Objective and Novelty Curve Sampling

TL;DR

This paper introduces a neural sentence expander trained on fiction data, using a novel focused objective and curve sampling to generate creative, understandable, and meaning-preserving sentence enhancements evaluated favorably by humans.

Contribution

It presents a new neural sentence expansion method with a focused training objective and novelty sampling, tailored for creative sentence enhancement tasks.

Findings

Generated expansions are comparable to original human sentences.

The method outperforms baseline models in human preference.

Expansions are understandable and meaning-preserving.

Abstract

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.