Non-task-oriented dialogue system considering user’s preference and human relations

Shunya Kobyashi, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a non-task-oriented dialogue system considering user’s preference and human relations. The proposed system has the following two features. First, the system estimates user’s emotions from the analysis results of user’s utterances and stores the individual preference with specific nouns. It allows the system to determine more suitable topics and answer sentences. Second, the system estimates user’s human relations from the analysis of user-to-user acquaintance relationship and similarity of preferences. It makes user more interested in conversation because the user can feel more familiar with the system. The performance of proposed system has been evaluated by subjective experiments. We confirmed the effectiveness of the proposed system, receiving higher score about user’s satisfaction than the conventional system.

Original languageEnglish
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume31
Issue number1
DOIs
Publication statusPublished - 2016 Jan 8

Fingerprint

Experiments

Keywords

  • Dialogue system
  • Emotion estimation
  • Natural language processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

@article{93183c07d79749b0a9f040ea0f471640,
title = "Non-task-oriented dialogue system considering user’s preference and human relations",
abstract = "In this paper, we propose a non-task-oriented dialogue system considering user’s preference and human relations. The proposed system has the following two features. First, the system estimates user’s emotions from the analysis results of user’s utterances and stores the individual preference with specific nouns. It allows the system to determine more suitable topics and answer sentences. Second, the system estimates user’s human relations from the analysis of user-to-user acquaintance relationship and similarity of preferences. It makes user more interested in conversation because the user can feel more familiar with the system. The performance of proposed system has been evaluated by subjective experiments. We confirmed the effectiveness of the proposed system, receiving higher score about user’s satisfaction than the conventional system.",
keywords = "Dialogue system, Emotion estimation, Natural language processing",
author = "Shunya Kobyashi and Masafumi Hagiwara",
year = "2016",
month = "1",
day = "8",
doi = "10.1527/tjsai.DSF-502",
language = "English",
volume = "31",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - Non-task-oriented dialogue system considering user’s preference and human relations

AU - Kobyashi, Shunya

AU - Hagiwara, Masafumi

PY - 2016/1/8

Y1 - 2016/1/8

N2 - In this paper, we propose a non-task-oriented dialogue system considering user’s preference and human relations. The proposed system has the following two features. First, the system estimates user’s emotions from the analysis results of user’s utterances and stores the individual preference with specific nouns. It allows the system to determine more suitable topics and answer sentences. Second, the system estimates user’s human relations from the analysis of user-to-user acquaintance relationship and similarity of preferences. It makes user more interested in conversation because the user can feel more familiar with the system. The performance of proposed system has been evaluated by subjective experiments. We confirmed the effectiveness of the proposed system, receiving higher score about user’s satisfaction than the conventional system.

AB - In this paper, we propose a non-task-oriented dialogue system considering user’s preference and human relations. The proposed system has the following two features. First, the system estimates user’s emotions from the analysis results of user’s utterances and stores the individual preference with specific nouns. It allows the system to determine more suitable topics and answer sentences. Second, the system estimates user’s human relations from the analysis of user-to-user acquaintance relationship and similarity of preferences. It makes user more interested in conversation because the user can feel more familiar with the system. The performance of proposed system has been evaluated by subjective experiments. We confirmed the effectiveness of the proposed system, receiving higher score about user’s satisfaction than the conventional system.

KW - Dialogue system

KW - Emotion estimation

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=84953896563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953896563&partnerID=8YFLogxK

U2 - 10.1527/tjsai.DSF-502

DO - 10.1527/tjsai.DSF-502

M3 - Article

AN - SCOPUS:84953896563

VL - 31

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -