Mixed Reference Interpretation in Multi-turn Conversation

Nanase Otake, Shoya Matsumori, Yosuke Fukuchi, Yusuke Takimoto, Michita Imai

Abstract

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.

Download


Paper Citation


in Harvard Style

Otake N., Matsumori S., Fukuchi Y., Takimoto Y. and Imai M. (2021). Mixed Reference Interpretation in Multi-turn Conversation.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-484-8, pages 321-328. DOI: 10.5220/0010260103210328


in Bibtex Style

@conference{icaart21,
author={Nanase Otake and Shoya Matsumori and Yosuke Fukuchi and Yusuke Takimoto and Michita Imai},
title={Mixed Reference Interpretation in Multi-turn Conversation},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2021},
pages={321-328},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010260103210328},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Mixed Reference Interpretation in Multi-turn Conversation
SN - 978-989-758-484-8
AU - Otake N.
AU - Matsumori S.
AU - Fukuchi Y.
AU - Takimoto Y.
AU - Imai M.
PY - 2021
SP - 321
EP - 328
DO - 10.5220/0010260103210328