Presentation information

Organized Session

Organized Session » OS-7

[2N5-OS-7a] 人間と共生する対話知能(1/2)

Wed. Jun 15, 2022 3:20 PM - 5:00 PM Room N (Room 501)

オーガナイザ:吉川 雄一郎(大阪大学)、東中 竜一郎(名古屋大学)[現地]、新保 史生(慶應義塾大学)

4:20 PM - 4:40 PM

[2N5-OS-7a-04] Conversational system that talks about the scenery seen from vehicles

〇Hiroaki Sugiyama1, Ko Koga2, Toshifumi Nishijima2 (1. Nippon Telegraph and Telecommunication, 2. Toyota Motor Corporation)

Keywords:Conversational systems, Large-scale Transformer model, Image grounded conversation

Conventional research on transformer-based chatting systems often focuses on text-closed dialogues. In addition, the use of images is limited to speech to introduce a topic based on the recognition results of one or a few images.
In this study, we propose a dialogue system that uses the changing scenery seen from a vehicle as a topic of conversation. Our system introduces external knowledge about buildings or scenery spots in the vicinity of the current location to make utterances.

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.