Disambiguation in Natural Language Interpretation Based on Amount of Information

Kazuo SUMITA; Teruhiko UKITA; Shin-ya AMANO

Disambiguation in Natural Language Interpretation Based on Amount of Information

Kazuo SUMITA, Teruhiko UKITA, Shin-ya AMANO

Full Text Views

0

Cite this

Summary :

This paper describes how to use the amount of information in a sentence interpretation as a measure of interpreting input sentences in a natural language understanding system. In this paper, an interpretation of a sentence is considered to be a proposition, and the amount of information of the interpretation is defined according to a listener's model with a knowledge base composed of a literal set and a logical implication set, both of which are defined within the framework of propositional logic. When a given sentence can be analyzed syntactically and semantically into more than one interpretation, the most informative interpretation is selected. The theory of selecting the most informative interpretation by the proposed measure is reasonable in the sense that communication is an act whereby messages are passed on with the least possible effort. The presented theory for disambiguation is applied to a practical procedure for anaphoric ambiguity resolution, as an example of the disambiguation problem, which forms part of a question-answering system. Furthermore, a conversation experiment was carried out, and it was found that ninety-three percent of referents corresponding to anaphoric expressions could be correctly chosen.

Publication: IEICE TRANSACTIONS on Information Vol.E74-D No.6 pp.1735-1746

Publication Date: 1991/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Artificial Intelligence and Cognitive Science

Authors

Kazuo SUMITA
Teruhiko UKITA
Shin-ya AMANO

Keyword

Cite this

Copy

Kazuo SUMITA, Teruhiko UKITA, Shin-ya AMANO, "Disambiguation in Natural Language Interpretation Based on Amount of Information" in IEICE TRANSACTIONS on Information, vol. E74-D, no. 6, pp. 1735-1746, June 1991, doi: .
Abstract: This paper describes how to use the amount of information in a sentence interpretation as a measure of interpreting input sentences in a natural language understanding system. In this paper, an interpretation of a sentence is considered to be a proposition, and the amount of information of the interpretation is defined according to a listener's model with a knowledge base composed of a literal set and a logical implication set, both of which are defined within the framework of propositional logic. When a given sentence can be analyzed syntactically and semantically into more than one interpretation, the most informative interpretation is selected. The theory of selecting the most informative interpretation by the proposed measure is reasonable in the sense that communication is an act whereby messages are passed on with the least possible effort. The presented theory for disambiguation is applied to a practical procedure for anaphoric ambiguity resolution, as an example of the disambiguation problem, which forms part of a question-answering system. Furthermore, a conversation experiment was carried out, and it was found that ninety-three percent of referents corresponding to anaphoric expressions could be correctly chosen.
URL: https://global.ieice.org/en_transactions/information/10.1587/e74-d_6_1735/_p

Copy

@ARTICLE{e74-d_6_1735,
author={Kazuo SUMITA, Teruhiko UKITA, Shin-ya AMANO, },
journal={IEICE TRANSACTIONS on Information},
title={Disambiguation in Natural Language Interpretation Based on Amount of Information},
year={1991},
volume={E74-D},
number={6},
pages={1735-1746},
abstract={This paper describes how to use the amount of information in a sentence interpretation as a measure of interpreting input sentences in a natural language understanding system. In this paper, an interpretation of a sentence is considered to be a proposition, and the amount of information of the interpretation is defined according to a listener's model with a knowledge base composed of a literal set and a logical implication set, both of which are defined within the framework of propositional logic. When a given sentence can be analyzed syntactically and semantically into more than one interpretation, the most informative interpretation is selected. The theory of selecting the most informative interpretation by the proposed measure is reasonable in the sense that communication is an act whereby messages are passed on with the least possible effort. The presented theory for disambiguation is applied to a practical procedure for anaphoric ambiguity resolution, as an example of the disambiguation problem, which forms part of a question-answering system. Furthermore, a conversation experiment was carried out, and it was found that ninety-three percent of referents corresponding to anaphoric expressions could be correctly chosen.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Disambiguation in Natural Language Interpretation Based on Amount of Information
T2 - IEICE TRANSACTIONS on Information
SP - 1735
EP - 1746
AU - Kazuo SUMITA
AU - Teruhiko UKITA
AU - Shin-ya AMANO
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E74-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1991
AB - This paper describes how to use the amount of information in a sentence interpretation as a measure of interpreting input sentences in a natural language understanding system. In this paper, an interpretation of a sentence is considered to be a proposition, and the amount of information of the interpretation is defined according to a listener's model with a knowledge base composed of a literal set and a logical implication set, both of which are defined within the framework of propositional logic. When a given sentence can be analyzed syntactically and semantically into more than one interpretation, the most informative interpretation is selected. The theory of selecting the most informative interpretation by the proposed measure is reasonable in the sense that communication is an act whereby messages are passed on with the least possible effort. The presented theory for disambiguation is applied to a practical procedure for anaphoric ambiguity resolution, as an example of the disambiguation problem, which forms part of a question-answering system. Furthermore, a conversation experiment was carried out, and it was found that ninety-three percent of referents corresponding to anaphoric expressions could be correctly chosen.
ER -