Abstract
In today's society, chat robots have entered people's vision. They can mainly carry out corresponding human-computer interaction, and are also research hotspots in the field of science and technology. Chat robots can build models to understand the input content, and then output relatively natural answers. In recent years, their birth has also produced a certain range of applications. However, the most representative chat robots are mainly based on retrieval and generation. Their patterns are different, so their behavior is also different. At the same time, in order to enable users to choose better chat robots, this paper compares the performance of retrieval chat robots based on SMN model, retrieval chat robots based on DAM model and seq2seq generation chat robots respectively. Their performance was analyzed and evaluated, mainly from the appropriateness and diversity of their responses and the difficulty of the training model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
