Text Morphing

TL;DR

This paper introduces text morphing, a new natural language generation task focused on creating smooth intermediate sentences between two given sentences, using a novel neural network approach.

Contribution

The paper proposes the Morphing Networks, combining editing vector generation and sentence editing, for the first time to address the text morphing task.

Findings

Outperforms baseline methods on text morphing accuracy

Successfully generates fluent intermediate sentences

Utilizes 10 million text sequences from Yelp dataset

Abstract

In this paper, we introduce a novel natural language generation task, termed as text morphing, which targets at generating the intermediate sentences that are fluency and smooth with the two input sentences. We propose the Morphing Networks consisting of the editing vector generation networks and the sentence editing networks which are trained jointly. Specifically, the editing vectors are generated with a recurrent neural networks model from the lexical gap between the source sentence and the target sentence. Then the sentence editing networks iteratively generate new sentences with the current editing vector and the sentence generated in the previous step. We conduct experiments with 10 million text morphing sequences which are extracted from the Yelp review dataset. Experiment results show that the proposed method outperforms baselines on the text morphing task. We also discuss directions and opportunities for future research of text morphing.