Text Morphing
This addresses a novel natural language generation task for applications requiring smooth text transitions, though it appears incremental in approach.
The paper tackles the problem of generating fluent intermediate sentences between two input sentences, introducing a new task called text morphing. Their proposed Morphing Networks method outperforms baselines on this task using 10 million sequences extracted from Yelp reviews.
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.