Masaya Ohagi — accepted AI-conference papers

2025

Persona-Consistent Dialogue Generation via Pseudo Preference Tuning

Junya Takayama, Masaya Ohagi, Tomoya Mizumoto, Katsumasa Yoshikawa

COLING 2025main

We propose a simple yet effective method for enhancing persona consistency in dialogue response generation using Direct Preference Optimization (DPO). In our method, we generate responses from the response generation model using persona information that has been randomly swapped with data from other…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

Dialogue Systems Can Generate Appropriate Responses without the Use of Question Marks?– a Study of the Effects of “?” for Spoken Dialogue Systems –

Tomoya Mizumoto, Takato Yamazaki, Katsumasa Yoshikawa, Masaya Ohagi, Toshiki Kawamoto, Toshinori Sato

COLING 2024main

When individuals engage in spoken discourse, various phenomena can be observed that differ from those that are apparent in text-based conversation. While written communication commonly uses a question mark to denote a query, in spoken discourse, queries are frequently indicated by a rising intonatio…

Cited by 1 Source ↗PDF ↗Scholar ↗