Generating Sentences by Editing Prototypes

Abstract

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.

14 pages, Transactions of the Association for Computational Linguistics (TACL), 2018

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems

Cited by in corpus (22)

• An efficient framework for learning sentence representations
• Learning to Represent Edits
• Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
• Avoiding Latent Variable Collapse With Generative Skip Models
• Semi-Amortized Variational Autoencoders
• Eval all, trust a few, do wrong to none: Comparing sentence generation models
• A Tutorial on Deep Latent Variable Models of Natural Language
• Variational Knowledge Graph Reasoning
• Retrieve and Refine: Improved Sequence Generation Models For Dialogue
• Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
• Preventing Posterior Collapse with delta-VAEs
• Fast Cross-domain Data Augmentation through Neural Sentence Editing
• Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
• Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
• QuickEdit: Editing Text & Translations by Crossing Words Out
• Extending Neural Generative Conversational Model using External Knowledge Sources
• Siamese Networks for Semantic Pattern Similarity
• Enriching Article Recommendation with Phrase Awareness
• Composition and decomposition of GANs
• Generating Contradictory, Neutral, and Entailing Sentences