Abstract
Human-computer dialogues in natural language will in many respects not resemble human dialogues. The main reasons for this are that there are differences in the communication channel, and also that the computer differs from a human as dialogue partner. But there are also other reasons. In this paper we first give some theoretical arguments in support of this position. It is concluded that current research in natural language and human computer interfaces needs to be supplemented by empirical studies aiming at uncovering the unique qualities of human-computer communication in natural language. In the second part we describe an environment for experiments and the results obtained. It is concluded that the main problem today is probably not syntax or speech-act capabilities, but computational methods for handling dialogue phenomena.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.