TY - JOUR PY - 2022// TI - Driving dialogue dataset collection and analysis for a transformer-based conversational system that talks about scenery JO - Transactions of Society of Automotive Engineers of Japan A1 - Koga, Ko A1 - Nishijima, Toshifumi A1 - Sugiyama, Hiroaki SP - 1134 EP - 1139 VL - 53 IS - 6 N2 - In order to develop a Transformer-based spoken dialogue system for natural dialogue about the scenery like a passenger, we collected a dataset of dialogue between role of drivers and passengers who engaged in a dialogue by sharing scenery driving movies by online. The collected dataset was analyzed to determine the extent to which utterances that talked about scenery or involved self-disclosure occur. The results showed that basic chit-chat performance was most important, even for chit-chat dialogues that talks about scenery.
Language: ja
LA - ja SN - 0287-8321 UR - http://dx.doi.org/10.11351/jsaeronbun.53.1134 ID - ref1 ER -