Analyzing Utterance Selection for Unnoticeable Topic Induction in Target-Guided Conversation Systems

Kai Yoshida, Koichiro Yoshino


Abstract
Target-guided conversation systems conduct dialogues to achieve predefined conversation targets, such as recommending target goods or talking about target topics. In such systems, it is important to transition topics naturally toward the target without letting the user notice the intention behind the topic induction. In this study, we implement a surprisal-based framework that quantifies the sense of induction, target awareness, and naturalness of system utterances by computing surprisal using an external language model. Experimental results from dialogue sessions demonstrate that utterance selection based on the proposed surprisal-based evaluation reduces the perceived induction of system utterances. Furthermore, correlation analysis reveals that the proposed metric aligns with human perception of induction. We also observe that surprisal values with respect to the target gradually decrease as the conversation progresses, indicating that the model implicitly learns to approach the target more naturally over time.
Anthology ID:
2026.iwsds-1.12
Volume:
Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
Month:
February
Year:
2026
Address:
Trento, Italy
Editors:
Giuseppe Riccardi, Seyed Mahed Mousavi, Maria Ines Torres, Koichiro Yoshino, Zoraida Callejas, Shammur Absar Chowdhury, Yun-Nung Chen, Frederic Bechet, Joakim Gustafson, Géraldine Damnati, Alex Papangelis, Luis Fernando D’Haro, John Mendonça, Raffaella Bernardi, Dilek Hakkani-Tur, Giuseppe "Pino" Di Fabbrizio, Tatsuya Kawahara, Firoj Alam, Gokhan Tur, Michael Johnston
Venue:
IWSDS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
114–122
Language:
URL:
https://aclanthology.org/2026.iwsds-1.12/
DOI:
Bibkey:
Cite (ACL):
Kai Yoshida and Koichiro Yoshino. 2026. Analyzing Utterance Selection for Unnoticeable Topic Induction in Target-Guided Conversation Systems. In Proceedings of the 16th International Workshop on Spoken Dialogue System Technology, pages 114–122, Trento, Italy. Association for Computational Linguistics.
Cite (Informal):
Analyzing Utterance Selection for Unnoticeable Topic Induction in Target-Guided Conversation Systems (Yoshida & Yoshino, IWSDS 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwsds-1.12.pdf