An Empirical Study on Deep Neural Network Models for Chinese Dialogue Generation

Symmetry

Xiuhong Li¹  Wushour Silamu¹  Zunwang Ke²  Jiabao Sheng²  Mieradilijiang Maimaiti³  Qinyong Wang⁴  Zhe Li⁵ 

[1] College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China;College of Software, Xinjiang University, Urumqi 830046, China;Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China;School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, QLD 4702, Australia;Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang Multilingual Information Technology Research Center, College of Software, Xinjiang University, Urumqi 830046, China;

关键词: natural language processing;    dialogue generation;    deep learning;    network architecture;    empirical investigation;   

DOI  :  10.3390/sym12111756

来源: DOAJ

【 摘 要 】

The task of dialogue generation has attracted increasing attention due to its diverse downstream applications, such as question-answering systems and chatbots. Recently, the deep neural network (DNN)-based dialogue generation models have achieved superior performance against conventional models utilizing statistical machine learning methods. However, despite that an enormous number of state-of-the-art DNN-based models have been proposed, there lacks detailed empirical comparative analysis for them on the open Chinese corpus. As a result, relevant researchers and engineers might find it hard to get an intuitive understanding of the current research progress. To address this challenge, we conducted an empirical study for state-of-the-art DNN-based dialogue generation models in various Chinese corpora. Specifically, extensive experiments were performed on several well-known single-turn and multi-turn dialogue corpora, including KdConv, Weibo, and Douban, to evaluate a wide range of dialogue generation models that are based on the symmetrical architecture of Seq2Seq, RNNSearch, transformer, generative adversarial nets, and reinforcement learning respectively. Moreover, we paid special attention to the prevalent pre-trained model for the quality of dialogue generation. Their performances were evaluated by four widely-used metrics in this area: BLEU, pseudo, distinct, and rouge. Finally, we report a case study to show example responses generated by these models separately.

【 授权许可】

Unknown