User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues

Kazunori Komatani, Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano


Abstract
We have been addressing the problem of acquiring attributes of unknown terms through dialogues and previously proposed an approach using the implicit confirmation process. It is crucial for dialogue systems to ask questions that do not diminish the user’s willingness to talk. In this paper, we conducted a user study to investigate user impression for several question types, including explicit and implicit, to acquire lexical knowledge. We clarified the order among the types and found that repeating the same question type annoys the user and degrades user impression even when the content of the questions is correct. We also propose a method for determining whether an estimated attribute is correct, which is included in an implicit question. The method exploits multiple-user responses to implicit questions about the attribute of the same unknown term. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly estimated attributes than when only single-user responses were considered.
Anthology ID:
2022.dnd-13.4
Volume:
Dialogue Discourse Volume 13
Month:
June
Year:
2022
Address:
Chicago, Illinois, USA
Editors:
Amanda Stent, Barbara Di Eugenio, Massimo Poesio, Kallirroi Georgila, Manfred Stede
Venue:
DND
SIG:
SIGDIAL
Publisher:
University of Illinois Chicago
Note:
Pages:
96–122
Language:
URL:
https://aclanthology.org/2022.dnd-13.4/
DOI:
10.5210/dad.2022.104
Bibkey:
Cite (ACL):
Kazunori Komatani, Kohei Ono, Ryu Takeda, Eric Nichols, and Mikio Nakano. 2022. User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues. Dialogue & Discourse, 13:96–122.
Cite (Informal):
User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues (Komatani et al., DND 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dnd-13.4.pdf