Interactive Dialogue Interface for Personalized News Article Comprehension

Tomoya Higuchi, Michimasa Inaba


Abstract
We developed an interface to explain news articles through dialogue by considering the user’s comprehension level. The interface generates several pertinent questions based on the ongoing dialogue and news article, and users advance the conversation by selecting a question. Based on the user’s selected questions, the interface estimates their comprehension level of the news article and adjusts the difficulty of the generated questions accordingly. This enables a personalized dialogue tailored to each user’s comprehension needs. The results of the baseline comparison experiments confirmed the usefulness of the interface.
Anthology ID:
2024.sigdial-1.29
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
329–332
Language:
URL:
https://aclanthology.org/2024.sigdial-1.29
DOI:
10.18653/v1/2024.sigdial-1.29
Bibkey:
Cite (ACL):
Tomoya Higuchi and Michimasa Inaba. 2024. Interactive Dialogue Interface for Personalized News Article Comprehension. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 329–332, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
Interactive Dialogue Interface for Personalized News Article Comprehension (Higuchi & Inaba, SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.29.pdf