D-PAGE: Diverse Paraphrase Generation

Abstract

In this paper, we investigate the diversity aspect of paraphrase generation. Prior deep learning models employ either decoding methods or add random input noise for varying outputs. We propose a simple method Diverse Paraphrase Generation (D-PAGE), which extends neural machine translation (NMT) models to support the generation of diverse paraphrases with implicit rewriting patterns. Our experimental results on two real-world benchmark datasets demonstrate that our model generates at least one order of magnitude more diverse outputs than the baselines in terms of a new evaluation metric Jeffrey's Divergence. We have also conducted extensive experiments to understand various properties of our model with a focus on diversity.

Cited by in corpus (9)

• One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases
• Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
• Towards Effective Paraphrasing for Information Disguise
• Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
• Paraphrase Generation as Unsupervised Machine Translation
• Generating Diverse Translation by Manipulating Multi-Head Attention
• multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning
• SPMoE: Generate Multiple Pattern-Aware Outputs with Sparse Pattern Mixture of Experts
• ConRPG: Paraphrase Generation using Contexts as Regularizer