D-PAGE: Diverse Paraphrase Generation

2018/08/13 by Xu, Qiongkai, Zhang, Juyan, Qu, Lizhen +2
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1808.04364

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.

Related

• Paraphrase Generation as Zero-Shot Multilingual Translation:\n Disentangling Semantic Similarity from Lexical and Syntactic Diversity
• Towards Diverse Paraphrase Generation Using Multi-Class Wasserstein GAN
• ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via\n Lexically-constrained Neural Machine Translation
• Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
• Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising