Generating Sentences by Editing Prototypes
arXiv:1709.08878
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.
arXiv comment14 pages, Transactions of the Association for Computational Linguistics (TACL), 2018
References in corpus (8)
- Efficient Estimation of Word Representations in Vector Space
- Auto-Encoding Variational Bayes
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Tutorial on Variational Autoencoders
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
- Search Engine Guided Non-Parametric Neural Machine Translation
Cited by in corpus (23)
- 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
- Adversarially Regularized Autoencoders
- Avoiding Latent Variable Collapse With Generative Skip Models
- Semi-Amortized Variational Autoencoders
- A Tutorial on Deep Latent Variable Models of Natural Language
- Eval all, trust a few, do wrong to none: Comparing sentence generation models
- 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
- Extending Neural Generative Conversational Model using External Knowledge Sources
- QuickEdit: Editing Text & Translations by Crossing Words Out
- Siamese Networks for Semantic Pattern Similarity
- Composition and decomposition of GANs
- Enriching Article Recommendation with Phrase Awareness
- Generating Contradictory, Neutral, and Entailing Sentences