Discourse Embellishment Using a Deep Encoder-Decoder Network

TL;DR

This paper introduces a new discourse generation task called textual embellishment, which enhances the complexity of generated text to produce more literary narratives, using deep encoder-decoder networks trained on a new dataset.

Contribution

It defines the task of textual embellishment for computational storytelling and demonstrates initial results with LSTM encoder-decoder models trained on a novel dataset.

Findings

Promising initial results on embellishment quality

Introduction of the 'Compiled Computer Tales' corpus

Potential for lightweight, domain-independent NLG systems

Abstract

We suggest a new NLG task in the context of the discourse generation pipeline of computational storytelling systems. This task, textual embellishment, is defined by taking a text as input and generating a semantically equivalent output with increased lexical and syntactic complexity. Ideally, this would allow the authors of computational storytellers to implement just lightweight NLG systems and use a domain-independent embellishment module to translate its output into more literary text. We present promising first results on this task using LSTM Encoder-Decoder networks trained on the WikiLarge dataset. Furthermore, we introduce "Compiled Computer Tales", a corpus of computationally generated stories, that can be used to test the capabilities of embellishment algorithms.