A proposal of topic map based Chatterbot for non-English natural language input

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a Chatterbot that returns an answer relevant to a question submitted by a user. We focus on non-English language, whose structure is more flexible. This requires a new framework to analyze the question. Our method divides the question sentence into triples, each of which is a combination of a noun, a particle, and a predicate. Expecting intelligent response to the question, we introduced the topic map which associates the units to suitable answers. In order to absorb the variant of particle usage, we applied cluster analysis to questions in Yahoo! Answers to group particles.

LanguageEnglish
Title of host publicationProcedia Computer Science
PublisherElsevier
Pages841-849
Number of pages9
Volume60
Edition1
DOIs
StatePublished - 2015
Event19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015 - , Singapore
Duration: 2015 Sep 72015 Sep 9

Other

Other19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015
CountrySingapore
Period15/9/715/9/9

Fingerprint

Cluster analysis

Keywords

  • Chatterbot
  • Clustering
  • Natural language processing
  • Particles
  • Topic maps

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Kimura, M. (2015). A proposal of topic map based Chatterbot for non-English natural language input. In Procedia Computer Science (1 ed., Vol. 60, pp. 841-849). Elsevier. DOI: 10.1016/j.procs.2015.08.247

A proposal of topic map based Chatterbot for non-English natural language input. / Kimura, Masaomi.

Procedia Computer Science. Vol. 60 1. ed. Elsevier, 2015. p. 841-849.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kimura, M 2015, A proposal of topic map based Chatterbot for non-English natural language input. in Procedia Computer Science. 1 edn, vol. 60, Elsevier, pp. 841-849, 19th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES 2015, Singapore, 15/9/7. DOI: 10.1016/j.procs.2015.08.247
Kimura M. A proposal of topic map based Chatterbot for non-English natural language input. In Procedia Computer Science. 1 ed. Vol. 60. Elsevier. 2015. p. 841-849. Available from, DOI: 10.1016/j.procs.2015.08.247
Kimura, Masaomi. / A proposal of topic map based Chatterbot for non-English natural language input. Procedia Computer Science. Vol. 60 1. ed. Elsevier, 2015. pp. 841-849
@inproceedings{5165683b1b504f27b1b9326efcb3ce01,
title = "A proposal of topic map based Chatterbot for non-English natural language input",
abstract = "In this paper, we propose a Chatterbot that returns an answer relevant to a question submitted by a user. We focus on non-English language, whose structure is more flexible. This requires a new framework to analyze the question. Our method divides the question sentence into triples, each of which is a combination of a noun, a particle, and a predicate. Expecting intelligent response to the question, we introduced the topic map which associates the units to suitable answers. In order to absorb the variant of particle usage, we applied cluster analysis to questions in Yahoo! Answers to group particles.",
keywords = "Chatterbot, Clustering, Natural language processing, Particles, Topic maps",
author = "Masaomi Kimura",
year = "2015",
doi = "10.1016/j.procs.2015.08.247",
language = "English",
volume = "60",
pages = "841--849",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",
edition = "1",

}

TY - GEN

T1 - A proposal of topic map based Chatterbot for non-English natural language input

AU - Kimura,Masaomi

PY - 2015

Y1 - 2015

N2 - In this paper, we propose a Chatterbot that returns an answer relevant to a question submitted by a user. We focus on non-English language, whose structure is more flexible. This requires a new framework to analyze the question. Our method divides the question sentence into triples, each of which is a combination of a noun, a particle, and a predicate. Expecting intelligent response to the question, we introduced the topic map which associates the units to suitable answers. In order to absorb the variant of particle usage, we applied cluster analysis to questions in Yahoo! Answers to group particles.

AB - In this paper, we propose a Chatterbot that returns an answer relevant to a question submitted by a user. We focus on non-English language, whose structure is more flexible. This requires a new framework to analyze the question. Our method divides the question sentence into triples, each of which is a combination of a noun, a particle, and a predicate. Expecting intelligent response to the question, we introduced the topic map which associates the units to suitable answers. In order to absorb the variant of particle usage, we applied cluster analysis to questions in Yahoo! Answers to group particles.

KW - Chatterbot

KW - Clustering

KW - Natural language processing

KW - Particles

KW - Topic maps

UR - http://www.scopus.com/inward/record.url?scp=84941104609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941104609&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2015.08.247

DO - 10.1016/j.procs.2015.08.247

M3 - Conference contribution

VL - 60

SP - 841

EP - 849

BT - Procedia Computer Science

PB - Elsevier

ER -