Exploring Diverse Expressions for Paraphrase Generation

• DOI: 10.18653/v1/d19-1313
• Publication Date: 2019-11-03T02:21:11Z
• Authors: Lihua Qian; Lin Qiu; Weinan Zhang; Xin Jiang; Yong Yu
• Keywords: 01 natural sciences; 0105 earth and related environmental sciences

Paraphrasing plays an important role in various natural language processing (NLP) tasks, such as question answering, information retrieval and sentence simplification. Recently, neural generative models have shown promising results in paraphrase generation. However, prior work mainly focused on single paraphrase generation, while ignoring the fact that diversity is essential for enhancing generalization capability and robustness of downstream applications. Few works have been done to solve diverse paraphrase generation. In this paper, we propose a novel approach with two discriminators and multiple generators to generate a variety of different paraphrases. A reinforcement learning algorithm is applied to train our model. Our experiments on two real-world datasets demonstrate that our model not only gains a significant increase in diversity but also improves generation quality over several state-of-the-art baselines.