An Empirical Study on Deep Neural Network Models for Chinese Dialogue Generation
Open Access
- 23 October 2020
- Vol. 12 (11), 1756
- https://doi.org/10.3390/sym12111756
Abstract
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.Keywords
This publication has 16 references indexed in Scilit:
- Next Point-of-Interest Recommendation on Resource-Constrained Mobile DevicesPublished by Association for Computing Machinery (ACM) ,2020
- Relevance-Promoting Language Model for Short-Text ConversationProceedings of the AAAI Conference on Artificial Intelligence, 2020
- MuTual: A Dataset for Multi-Turn Dialogue ReasoningPublished by Association for Computational Linguistics (ACL) ,2020
- Enhancing Collaborative Filtering with Generative AugmentationPublished by Association for Computing Machinery (ACM) ,2019
- A Rapid Localization Method of Radiation Sources Used for Multi-Sensor NetworksPublished by Association for Computing Machinery (ACM) ,2018
- Neural Memory Streaming Recommender Networks with Adversarial TrainingPublished by Association for Computing Machinery (ACM) ,2018
- Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based ChatbotsPublished by Association for Computational Linguistics (ACL) ,2017
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational AutoencodersPublished by Association for Computational Linguistics (ACL) ,2017
- How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational ModelsPublished by Association for Computational Linguistics (ACL) ,2017
- Neural Responding Machine for Short-Text ConversationPublished by Association for Computational Linguistics (ACL) ,2015