Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

TL;DR

This paper introduces iNLG, a novel method that uses machine-generated images to guide open-ended text generation, enhancing coherence and informativeness in various creative writing tasks.

Contribution

We propose a new approach that integrates visual imagination into language models to improve open-ended text generation quality.

Findings

iNLG improves coherence and informativeness of generated texts

Effective across multiple tasks like story and concept-to-text generation

Validated by both automatic metrics and human evaluations

Abstract

Recent advances in text-to-image synthesis make it possible to visualize machine imaginations for a given context. On the other hand, when generating text, human writers are gifted at creative visualization, which enhances their writings by forming imaginations as blueprints before putting down the stories in words. Inspired by such a cognitive process, we ask the natural question of whether we can endow machines with the same ability to utilize visual information and construct a general picture of the context to guide text generation. In this work, we propose iNLG that uses machine-generated images to guide language models in open-ended text generation. The experiments and analyses demonstrate the effectiveness of iNLG on open-ended text generation tasks, including text completion, story generation, and concept-to-text generation in both few-shot and full-data scenarios. Both automatic metrics and human evaluations verify that the text snippets generated by our iNLG are coherent and informative while displaying minor degeneration.