Understanding Conversational Sentences Using Multi-Paradigm World Knowledge

Teruhiko UKITA; Satoshi KINOSHITA; Kazuo SUMITA; Hiroshi SANO; Shin'ya AMANO

Understanding Conversational Sentences Using Multi-Paradigm World Knowledge

Teruhiko UKITA, Satoshi KINOSHITA, Kazuo SUMITA, Hiroshi SANO, Shin'ya AMANO

Full Text Views

0

Cite this

Summary :

Resolving ambiguities in interpreting the user's utterances is one of the most fundamental problems in the development of a question-answering system. The process of disambiguating interpretations requires knowledge and inference functions on an objective task field. This paper describes a framework for understanding conversational language, using the multi-paradigm knowledge representation (frames" and rules") which represents concept hierarchy and causal relationships for an objective field. Knowledge of the objective field is used in the process to interpret input sentences as a model for the objective world. In interpreting sentences, a procedure judges preferences for interpretation candidates by identifying causal relationship with messages in the preceding context, where the causal relationship is used to supplement some shortage of information and to give either an affirmative or a negative explanation to the interpretation. The procedure has been implemented in an experimental question-answering system, whose current task is consultation in operating an electronic device. The experimental results are shown for a concrete problem involving resolving anaphoric references, and characteristics of the knowledge processing system are discussed.

Publication: IEICE TRANSACTIONS on Information Vol.E75-D No.3 pp.352-362

Publication Date: 1992/05/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Artificial Intelligence and Cognitive Science

Cite this

Copy

Teruhiko UKITA, Satoshi KINOSHITA, Kazuo SUMITA, Hiroshi SANO, Shin'ya AMANO, "Understanding Conversational Sentences Using Multi-Paradigm World Knowledge" in IEICE TRANSACTIONS on Information, vol. E75-D, no. 3, pp. 352-362, May 1992, doi: .
Abstract: Resolving ambiguities in interpreting the user's utterances is one of the most fundamental problems in the development of a question-answering system. The process of disambiguating interpretations requires knowledge and inference functions on an objective task field. This paper describes a framework for understanding conversational language, using the multi-paradigm knowledge representation (frames" and rules") which represents concept hierarchy and causal relationships for an objective field. Knowledge of the objective field is used in the process to interpret input sentences as a model for the objective world. In interpreting sentences, a procedure judges preferences for interpretation candidates by identifying causal relationship with messages in the preceding context, where the causal relationship is used to supplement some shortage of information and to give either an affirmative or a negative explanation to the interpretation. The procedure has been implemented in an experimental question-answering system, whose current task is consultation in operating an electronic device. The experimental results are shown for a concrete problem involving resolving anaphoric references, and characteristics of the knowledge processing system are discussed.
URL: https://global.ieice.org/en_transactions/information/10.1587/e75-d_3_352/_p

Copy

@ARTICLE{e75-d_3_352,
author={Teruhiko UKITA, Satoshi KINOSHITA, Kazuo SUMITA, Hiroshi SANO, Shin'ya AMANO, },
journal={IEICE TRANSACTIONS on Information},
title={Understanding Conversational Sentences Using Multi-Paradigm World Knowledge},
year={1992},
volume={E75-D},
number={3},
pages={352-362},
abstract={Resolving ambiguities in interpreting the user's utterances is one of the most fundamental problems in the development of a question-answering system. The process of disambiguating interpretations requires knowledge and inference functions on an objective task field. This paper describes a framework for understanding conversational language, using the multi-paradigm knowledge representation (frames" and rules") which represents concept hierarchy and causal relationships for an objective field. Knowledge of the objective field is used in the process to interpret input sentences as a model for the objective world. In interpreting sentences, a procedure judges preferences for interpretation candidates by identifying causal relationship with messages in the preceding context, where the causal relationship is used to supplement some shortage of information and to give either an affirmative or a negative explanation to the interpretation. The procedure has been implemented in an experimental question-answering system, whose current task is consultation in operating an electronic device. The experimental results are shown for a concrete problem involving resolving anaphoric references, and characteristics of the knowledge processing system are discussed.},
keywords={},
doi={},
ISSN={},
month={May},}

Copy

TY - JOUR
TI - Understanding Conversational Sentences Using Multi-Paradigm World Knowledge
T2 - IEICE TRANSACTIONS on Information
SP - 352
EP - 362
AU - Teruhiko UKITA
AU - Satoshi KINOSHITA
AU - Kazuo SUMITA
AU - Hiroshi SANO
AU - Shin'ya AMANO
PY - 1992
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E75-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - May 1992
AB - Resolving ambiguities in interpreting the user's utterances is one of the most fundamental problems in the development of a question-answering system. The process of disambiguating interpretations requires knowledge and inference functions on an objective task field. This paper describes a framework for understanding conversational language, using the multi-paradigm knowledge representation (frames" and rules") which represents concept hierarchy and causal relationships for an objective field. Knowledge of the objective field is used in the process to interpret input sentences as a model for the objective world. In interpreting sentences, a procedure judges preferences for interpretation candidates by identifying causal relationship with messages in the preceding context, where the causal relationship is used to supplement some shortage of information and to give either an affirmative or a negative explanation to the interpretation. The procedure has been implemented in an experimental question-answering system, whose current task is consultation in operating an electronic device. The experimental results are shown for a concrete problem involving resolving anaphoric references, and characteristics of the knowledge processing system are discussed.
ER -