Generating Sentences by Editing Prototypes
This addresses the problem of generating coherent and diverse sentences for natural language processing applications, representing an incremental advancement over traditional generative models.
The paper tackles sentence generation by proposing a prototype-then-edit model that samples a prototype from a corpus and edits it, improving perplexity in language modeling and generating higher quality outputs in human evaluations.
We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.