TY - GEN
T1 - Mixed reference interpretation in multi-turn conversation
AU - Otake, Nanase
AU - Matsumori, Shoya
AU - Fukuchi, Yosuke
AU - Takimoto, Yusuke
AU - Imai, Michita
N1 - Funding Information:
This work was supported by JST CREST Grant Number JPMJCR19A1, Japan.
Publisher Copyright:
© 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved
PY - 2021
Y1 - 2021
N2 - Contextual reference refers to the mention of matters or topics that appear in the conversation, and situational reference to the mention of objects or events that exist around the conversation participants. In conventional utterance processing, the system deals with either contextual or situational reference in a dialogue. However, in order to achieve meaningful communication between people and the system in the real world, the system needs to consider Mixed Reference Interpretation (MRI) problem, that is, handling both types of reference in an integrated manner. In this paper, we propose DICONS, a method that sequentially estimates an interpretation of utterances from interpretation candidates derived from both contextual reference and situational reference in a dialogue. In an experiment in which DICONS handled this task with both contextual and situational references, we found that it could properly judge which type of reference had occurred. We also found that the referent of the demonstrative word in each context and situation could be properly estimated.
AB - Contextual reference refers to the mention of matters or topics that appear in the conversation, and situational reference to the mention of objects or events that exist around the conversation participants. In conventional utterance processing, the system deals with either contextual or situational reference in a dialogue. However, in order to achieve meaningful communication between people and the system in the real world, the system needs to consider Mixed Reference Interpretation (MRI) problem, that is, handling both types of reference in an integrated manner. In this paper, we propose DICONS, a method that sequentially estimates an interpretation of utterances from interpretation candidates derived from both contextual reference and situational reference in a dialogue. In an experiment in which DICONS handled this task with both contextual and situational references, we found that it could properly judge which type of reference had occurred. We also found that the referent of the demonstrative word in each context and situation could be properly estimated.
KW - Contextual reference
KW - Conversation context
KW - Demonstrative word interpretation
KW - Mixed reference interpretation
KW - Situational reference
UR - http://www.scopus.com/inward/record.url?scp=85103848710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85103848710&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85103848710
T3 - ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
SP - 321
EP - 328
BT - ICAART 2021 - Proceedings of the 13th International Conference on Agents and Artificial Intelligence
A2 - Rocha, Ana Paula
A2 - Steels, Luc
A2 - van den Herik, Jaap
PB - SciTePress
T2 - 13th International Conference on Agents and Artificial Intelligence, ICAART 2021
Y2 - 4 February 2021 through 6 February 2021
ER -