JSAI2024

Presentation information

Organized Session

Organized Session » OS-31

[1I5-OS-31b] OS-31

Tue. May 28, 2024 5:00 PM - 6:40 PM Room I (Room 41)

オーガナイザ:三宅 陽一郎(株式会社スクウェア・エニックス)、森川 幸人(モリカトロン株式会社)

5:00 PM - 5:20 PM

[1I5-OS-31b-01] Evaluation Model for Persona Characteristics via Contrastive Learning

〇Michimasa Inaba1 (1. The University of Electro-Communications)

Keywords:Dialogue Systems, Persona Characteristics

Persona-aware dialogue systems can improve the consistency of system responses, user trust, and enjoyment. Filtering nonpersona-like utterances is important for constructing these systems.
We proposed a novel model to capture the intensity of persona characteristics in a given utterance. We trained the model using contrastive learning, based on the similarity of the utterances' speaker. Experimental results showed that our model outperforms existing methods and baselines using pre-trained language models.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password