Q-Med: A Spoken-Language System to Conduct Medical Interviews

From Tetherless World Wiki

Jump to: navigation, search

Citation: Kevin Johnson and Alex Poon and Smadar Shiffman and Richard Lin and Lawrence M. Fagan. (1992) Q-Med: A Spoken-Language System to Conduct Medical Interviews. In KSL-92-09, February,1992.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Kevin Johnson and Alex Poon and Smadar Shiffman and Richard Lin and Lawrence M. Fagan
title Q-Med: A Spoken-Language System to Conduct Medical Interviews
number KSL-92-09
institution Knowledge Systems, AI Laboratory
year 1992
month February
Bibtex more
Access Paper
abstract Continuous-speech-recognition technology (CSRT) promises to be a useful modality for human-computer interaction. Unfortunately, usable spoken-language systems have been difficult to build, in part due to problems with misrecognitions when large speaker-independent vocabularies and language models are used. As part of a project to create spoken-language systems that achieve acceptable performance in spite of partially misrecognized input, we have developed Q-MED, a system that creates applications using CSRT in the task of medical interviewing. The system uses questions arranged hierarchically: from open-ended questions that have large language models, to more directed questions that use smaller language models. This hierarchy of questions allows the system to recover from unintended or misinterpreted utterances by asking more directed questions until an adequate answer is recognized. Furthermore, information-retrieval techniques map an utterance to one or more predefined symptoms, even if only some of the words in the utterance are recognized correctly. This paper discusses the rationale behind and implementation of Q-MED, using examples from an application created to interview patients who have abdominal pain.

KSL Technical Report ID: KSL-92-09
Facts about Q-Med: A Spoken-Language System to Conduct Medical InterviewsRDF feed
Abstract Continuous-speech-recognition technology ( … Continuous-speech-recognition technology (CSRT) promises to be a useful modality for human-computer interaction. Unfortunately, usable spoken-language systems have been difficult to build, in part due to problems with misrecognitions when large speaker-independent vocabularies and language models are used. As part of a project to create spoken-language systems that achieve acceptable performance in spite of partially misrecognized input, we have developed Q-MED, a system that creates applications using CSRT in the task of medical interviewing. The system uses questions arranged hierarchically: from open-ended questions that have large language models, to more directed questions that use smaller language models. This hierarchy of questions allows the system to recover from unintended or misinterpreted utterances by asking more directed questions until an adequate answer is recognized. Furthermore, information-retrieval techniques map an utterance to one or more predefined symptoms, even if only some of the words in the utterance are recognized correctly. This paper discusses the rationale behind and implementation of Q-MED, using examples from an application created to interview patients who have abdominal pain. nterview patients who have abdominal pain.
Author Kevin Johnson and Alex Poon and Smadar Shiffman and Richard Lin and Lawrence M. Fagan  +
Bibtype techreport  +
Has author Kevin Johnson and Alex Poon and Smadar Shiffman and Richard Lin and Lawrence M. Fagan  +
Has identifier KSL-92-09  +
Has publishing details February,1992  +
Has title Q-Med: A Spoken-Language System to Conduct Medical Interviews  +
Has where published KSL-92-09  +
Has year 1992  +
Institution Knowledge Systems, AI Laboratory  +
Ksl tr id KSL-92-09  +
Month February  +
Number KSL-92-09  +
Process note NO  +
Title Q-Med: A Spoken-Language System to Conduct Medical Interviews  +
Year 1992  +
Retrieved from "http://tw.rpi.edu/wiki/Q-Med:_A_Spoken-Language_System_to_Conduct_Medical_Interviews"
Personal tools