AFPun-GAN:Ambiguity-Fluency Generative Adversarial Network for Pun Generation

摘要：

　　Automatic pun generation is an interesting and challenging text gen-eration task.In this study,we focus on the task of homographic pun generation by given a pair of word senses.Current efforts depend on templates or laboriously annotated pun source to guide the supervised learning,which is lack of quality and diversity of generated puns.To address this,we present a new text generation model,called Ambiguity-Fluency Pun Generative Adversarial Network(AFPun-GAN)for pun genration.This model is composed of a pun generator to produce pun sentences by a hierarchical on-lstm attention model,and a pun discriminator to distinguish the generated pun sentences and real sentences with word senses of target pun word.The proposed model assigns a hierarchical low reward to train the pun generator via reinforcement learning,encouraging the pun generator to produce the ambiguous and fluent pun sentences that can better support two word senses.The experimental results on pun generation task demonstrate that our proposed AFPun-GAN model is able to generate pun sentences that are more ambiguous and fluent in both automatic and human evaluation.

关键词： Pun generation Generative adversarial network Ambiguity Fluency

作者: Yufeng Diao Liang Yang Xiaochao Fan Yonghe Chu Di Wu Shaowu Zhang Hongfei Lin

作者单位: Dalian University of Technology,Dalian 116024,China;Inner Mongolia University for Nationalities,Tong Dalian University of Technology,Dalian 116024,China Dalian University of Technology,Dalian 116024,China;Xinjiang Normal University,Urumq 830054,China

会议类型: 国际会议

会议名称: 9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)

会议地点: 郑州

会议语种:英文

页码: 604-616

在线出版日期: 2020-10-14（万方平台首次上网日期，不代表论文的发表时间）