The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
논증은 전제와 반박을 통해 합의에 도달하는 과정이다. 인공적인 대화 시스템이 논쟁을 수행할 수 있다면 사용자의 결정과 다른 사람과의 협상 능력을 향상시킬 수 있습니다. 이전까지 연구자들은 논쟁 구조에 관한 구조화된 데이터베이스를 통해 논쟁 대화 시스템을 연구하고 대화의 논리적 일관성을 평가해 왔습니다. 그러나 이러한 시스템은 마지막 발화에 대한 사용자의 동의 또는 불일치에 따라 응답을 변경할 수 없습니다. 또한 생성된 대화의 설득력도 평가되지 않았습니다. 본 연구에서는 인간의 동의와 불일치를 고려한 계층적 주장 구조를 통해 설득력 있는 주장을 생성하는 방법을 제안한다. 설득력은 표시된 대화 텍스트에 대한 참가자의 서면 인상이 제3자 Likert 척도 평가를 통해 점수가 매겨지는 크라우드 소싱 플랫폼을 통해 평가됩니다. 제안된 방법은 사용자의 동의 여부를 고려하지 않고 논쟁 응답 텍스트를 생성하는 기본 방법과 비교되었다. 실험 결과는 제안한 방법이 기본 방법보다 더 설득력 있는 대화를 생성할 수 있음을 시사합니다. 추가 분석에서는 계층적 논증 구조에 내재된 대화 시스템의 행동 평가에 의해 인지된 설득력이 유도된다는 것을 암시했습니다.
Kazuki SAKAI
Osaka University,JST ERATO
Ryuichiro HIGASHINAKA
NTT Corporation
Yuichiro YOSHIKAWA
Osaka University,JST ERATO
Hiroshi ISHIGURO
Osaka University,JST ERATO
Junji TOMITA
NTT Corporation
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kazuki SAKAI, Ryuichiro HIGASHINAKA, Yuichiro YOSHIKAWA, Hiroshi ISHIGURO, Junji TOMITA, "Hierarchical Argumentation Structure for Persuasive Argumentative Dialogue Generation" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 2, pp. 424-434, February 2020, doi: 10.1587/transinf.2019EDP7147.
Abstract: Argumentation is a process of reaching a consensus through premises and rebuttals. If an artificial dialogue system can perform argumentation, it can improve users' decisions and ability to negotiate with the others. Previously, researchers have studied argumentative dialogue systems through a structured database regarding argumentation structure and evaluated the logical consistency of the dialogue. However, these systems could not change its response based on the user's agreement or disagreement to its last utterance. Furthermore, the persuasiveness of the generated dialogue has not been evaluated. In this study, a method is proposed to generate persuasive arguments through a hierarchical argumentation structure that considers human agreement and disagreement. Persuasiveness is evaluated through a crowd sourcing platform wherein participants' written impressions of shown dialogue texts are scored via a third person Likert scale evaluation. The proposed method was compared to the baseline method wherein argument response texts were generated without consideration of the user's agreement or disagreement. Experiment results suggest that the proposed method can generate a more persuasive dialogue than the baseline method. Further analysis implied that perceived persuasiveness was induced by evaluations of the behavior of the dialogue system, which was inherent in the hierarchical argumentation structure.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7147/_p
부
@ARTICLE{e103-d_2_424,
author={Kazuki SAKAI, Ryuichiro HIGASHINAKA, Yuichiro YOSHIKAWA, Hiroshi ISHIGURO, Junji TOMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Hierarchical Argumentation Structure for Persuasive Argumentative Dialogue Generation},
year={2020},
volume={E103-D},
number={2},
pages={424-434},
abstract={Argumentation is a process of reaching a consensus through premises and rebuttals. If an artificial dialogue system can perform argumentation, it can improve users' decisions and ability to negotiate with the others. Previously, researchers have studied argumentative dialogue systems through a structured database regarding argumentation structure and evaluated the logical consistency of the dialogue. However, these systems could not change its response based on the user's agreement or disagreement to its last utterance. Furthermore, the persuasiveness of the generated dialogue has not been evaluated. In this study, a method is proposed to generate persuasive arguments through a hierarchical argumentation structure that considers human agreement and disagreement. Persuasiveness is evaluated through a crowd sourcing platform wherein participants' written impressions of shown dialogue texts are scored via a third person Likert scale evaluation. The proposed method was compared to the baseline method wherein argument response texts were generated without consideration of the user's agreement or disagreement. Experiment results suggest that the proposed method can generate a more persuasive dialogue than the baseline method. Further analysis implied that perceived persuasiveness was induced by evaluations of the behavior of the dialogue system, which was inherent in the hierarchical argumentation structure.},
keywords={},
doi={10.1587/transinf.2019EDP7147},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - Hierarchical Argumentation Structure for Persuasive Argumentative Dialogue Generation
T2 - IEICE TRANSACTIONS on Information
SP - 424
EP - 434
AU - Kazuki SAKAI
AU - Ryuichiro HIGASHINAKA
AU - Yuichiro YOSHIKAWA
AU - Hiroshi ISHIGURO
AU - Junji TOMITA
PY - 2020
DO - 10.1587/transinf.2019EDP7147
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2020
AB - Argumentation is a process of reaching a consensus through premises and rebuttals. If an artificial dialogue system can perform argumentation, it can improve users' decisions and ability to negotiate with the others. Previously, researchers have studied argumentative dialogue systems through a structured database regarding argumentation structure and evaluated the logical consistency of the dialogue. However, these systems could not change its response based on the user's agreement or disagreement to its last utterance. Furthermore, the persuasiveness of the generated dialogue has not been evaluated. In this study, a method is proposed to generate persuasive arguments through a hierarchical argumentation structure that considers human agreement and disagreement. Persuasiveness is evaluated through a crowd sourcing platform wherein participants' written impressions of shown dialogue texts are scored via a third person Likert scale evaluation. The proposed method was compared to the baseline method wherein argument response texts were generated without consideration of the user's agreement or disagreement. Experiment results suggest that the proposed method can generate a more persuasive dialogue than the baseline method. Further analysis implied that perceived persuasiveness was induced by evaluations of the behavior of the dialogue system, which was inherent in the hierarchical argumentation structure.
ER -