ML Anthology

SIS: A Shell for Interview Systems

Atsuo Kawaguchi, Riichiro Mizoguchi, Takahira Yamaguchi, Osamu Kakusho
IJCAI 1987 pp. 359-361
/ijcai/1987/kawaguchi1987ijcai-sis/

Abstract

An interviewer has two kinds of knowledge. One is about a domain under consideration and the other is knowledge for interview itself which makes the interviewer an expert of interview. The latter seems to be independent of the domain because an experienced interviewer, such as a TV interviewer, can carry on his tasks in many fields. Furthermore, we believe that the interview knowledge consists of several interview knowledge primitives. Based on this idea, we are developing SIS, a Shell for Interview Systems which has seven question strategy primitives as the knowledge for interviewing. Generality and effectiveness of SIS are shown through two implementation examples of interview systems, I2s and MORE. The seven primitives are shown to be efficientfor the two system whose domains and tasks are entirely different.

PDF Semantic Scholar

Cite

Text

Kawaguchi et al. "SIS: A Shell for Interview Systems." International Joint Conference on Artificial Intelligence, 1987.

Markdown

[Kawaguchi et al. "SIS: A Shell for Interview Systems." International Joint Conference on Artificial Intelligence, 1987.](https://mlanthology.org/ijcai/1987/kawaguchi1987ijcai-sis/)

BibTeX

@inproceedings{kawaguchi1987ijcai-sis,
  title     = {{SIS: A Shell for Interview Systems}},
  author    = {Kawaguchi, Atsuo and Mizoguchi, Riichiro and Yamaguchi, Takahira and Kakusho, Osamu},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1987},
  pages     = {359-361},
  url       = {https://mlanthology.org/ijcai/1987/kawaguchi1987ijcai-sis/}
}