A Deep Generative Framework for Paraphrase Generation

Abstract

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed method is based on a combination of deep generative models (VAE) with sequence-to-sequence models (LSTM) to generate paraphrases, given an input sentence. Traditional VAEs when combined with recurrent neural networks can generate free text but they are not suitable for paraphrase generation for a given sentence. We address this problem by conditioning the both, encoder and decoder sides of VAE, on the original sentence, so that it can generate the given sentence's paraphrases. Unlike most existing models, our model is simple, modular and can generate multiple paraphrases, for a given sentence. Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence. Furthermore, we evaluate our method on a newly released question paraphrase dataset, and establish a new baseline for future research.

Cited by in corpus (15)

• Unsupervised Paraphrase Generation using Pre-trained Language Models
• Non-autoregressive Transformer by Position Learning
• Unsupervised Text Generation by Learning from Search
• Zero-Shot Paraphrase Generation with Multilingual Language Models
• PAWS: Paraphrase Adversaries from Word Scrambling
• Generating Sentences from Disentangled Syntactic and Semantic Spaces
• Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• Label Dependent Deep Variational Paraphrase Generation
• Syntax-Infused Variational Autoencoder for Text Generation
• Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
• Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way
• Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs
• How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions
• Generating Diverse Translation by Manipulating Multi-Head Attention