Papers by Masaya Ohagi

2 papers
Persona-Consistent Dialogue Generation via Pseudo Preference Tuning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for improving persona consistency in dialogues require external resources.
Approach: They propose a method for enhancing persona consistency in dialogue response generation using direct preference optimization using persona data.
Outcome: The proposed method produces more consistent and natural responses than previous methods.
Dialogue Systems Can Generate Appropriate Responses without the Use of Question Marks?– a Study of the Effects of “?” for Spoken Dialogue Systems – (2024.lrec-main)

Copied to clipboard

Challenge: Existing systems for spoken dialogues do not append question marks to recognized queries . lack of punctuation marks in spoken dialogue can negatively impact comprehension .
Approach: They investigate the impact of question marks on spoken dialogue systems . they analyze examples to determine which types of utterances have the impact .
Outcome: The proposed method shows that question marks have a significant impact on spoken dialogue systems.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations