How may I help you
Citations
3,794 citations
Cites background from "How may I help you"
...(University of Colorado, Boulder) Upper Saddle River, NJ: Prentice Hall (Prentice Hall series in artificial intelligence, edited by Stuart Russell and Peter Norvig), 2000, xxvi+934 pp; hardbound, ISBN 0-13-095069-6, $64.00 Reviewed by Virginia Teller Hunter College and the Graduate Center, The City…...
[...]
...(University of Colorado, Boulder) Upper Saddle River, NJ: Prentice Hall (Prentice Hall series in artificial intelligence, edited by Stuart Russell and Peter Norvig), 2000, xxvi+934 pp; hardbound, ISBN 0-13-095069-6, $64.00 Reviewed by Virginia Teller Hunter College and the Graduate Center, The City University of New York...
[...]
2,108 citations
972 citations
853 citations
697 citations
References
45,034 citations
"How may I help you" refers methods in this paper
...We remark that this is an approximation to the mutual information of Ž .the full n-tuple Cover and Thomas, 1991 ....
[...]
472 citations
Additional excerpts
...Wilpon et al., 1990 ....
[...]
224 citations
174 citations
"How may I help you" refers background in this paper
...Following this paradigm, we have constructed several devices which acquire the capability of understanding language via building statistical associations between input stimuli and appropriate machine Žresponses Gertner and Gorin, 1993; Gorin et al., 1994a; Miller and Gorin, 1993; Sankar and Gorin, .1993; Henis et al., 1994 ....
[...]
...…have constructed several devices which acquire the capability of understanding language via building statistical associations between input stimuli and appropriate machine Žresponses Gertner and Gorin, 1993; Gorin et al., 1994a; Miller and Gorin, 1993; Sankar and Gorin, .1993; Henis et al., 1994 ....
[...]
...We have explored Ž .this paradigm in some detail Gorin, 1995a , in particular contrasting it with traditional communication theory, where the goal is to reproduce a signal at some distant point....
[...]
...In previous experiments, salient words have been exploited to learn the mapping from unconstrained input to machine action for a Žvariety of tasks Gertner and Gorin, 1993; Gorin et al., 1994a,b; Henis et al., 1994; Miller and Gorin, .1993; Sankar and Gorin, 1993 ....
[...]
...We then introduce an additional between-channel criterion, which is that a fragment should have high information content for the call-action channel....
[...]