Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Junji Tomita"'
Publikováno v:
Multimodal Technologies and Interaction, Vol 3, Iss 4, p 70 (2019)
We investigated the mouth-opening transition pattern (MOTP), which represents the change of mouth-opening degree during the end of an utterance, and used it to predict the next speaker and utterance interval between the start time of the next speaker
Externí odkaz:
https://doaj.org/article/87dec523d543421f96f2e5f64c6742e1
Autor:
Yushi Aono, Katayama Taichi, Emi Yamaguchi, Masahiro Mizukami, Ryuichiro Higashinaka, Ryo Ishii, Koh Mitsuda, Hidetoshi Kawabata, Junji Tomita, Noritake Adachi
Publikováno v:
Journal of Information Processing. 29:30-44
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811593222
IWSDS
IWSDS
Towards creating an open-domain argumentative dialogue system, preparing a database of structured argumentative knowledge for the system as reported in previous work is difficult because diverse propositions exist in the open-domain setting. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc01052b8fe2c5d5ecc2e759da44cd5e
https://doi.org/10.1007/978-981-15-9323-9_7
https://doi.org/10.1007/978-981-15-9323-9_7
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811593222
IWSDS
IWSDS
We propose a model for generating head nods from an utterance text considering personality traits. We have been investigating the automatic generation of body motion, such as nodding, from utterance text in dialog agent systems. Human body motion var
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f43c978522af37ff27c855493a358d98
https://doi.org/10.1007/978-981-15-9323-9_26
https://doi.org/10.1007/978-981-15-9323-9_26
Autor:
Emi Yamaguchi, Katayama Taichi, Hidetoshi Kawabata, Junji Tomita, Masahiro Mizukami, Ryo Ishii, Noritake Adachi, Ryuichiro Higashinaka, Yushi Aono, Koh Mitsuda
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030601515
HCI (45)
HCI (45)
Many surely dream of being able to chat with his/her favorite anime characters from an early age. To make such a dream possible, we propose an efficient method for constructing a system that enables users to text chat with existing anime characters.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1f9857d797f55d15215b844c256b6d3
https://doi.org/10.1007/978-3-030-60152-2_25
https://doi.org/10.1007/978-3-030-60152-2_25
Publikováno v:
Multimodal Technologies and Interaction, Vol 3, Iss 4, p 70 (2019)
Multimodal Technologies and Interaction
Volume 3
Issue 4
Multimodal Technologies and Interaction
Volume 3
Issue 4
We investigated the mouth-opening transition pattern (MOTP), which represents the change of mouth-opening degree during the end of an utterance, and used it to predict the next speaker and utterance interval between the start time of the next speaker
Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pre-training language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44a2b9f7c0cdc1f36891b72b1d418a85
http://arxiv.org/abs/1905.12848
http://arxiv.org/abs/1905.12848
Estimating Interpersonal Reactivity Scores Using Gaze Behavior and Dialogue Act During Turn-Changing
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030219048
HCI (14)
HCI (14)
We explored the effectiveness of external observable behaviors in multi-party discussions to estimate an individual’s empathy skill level. In our previous research, we estimated personal empathy skills from the external observable behavior in multi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e80523f8deffd59b74b974f3975a631
https://doi.org/10.1007/978-3-030-21905-5_4
https://doi.org/10.1007/978-3-030-21905-5_4
Autor:
Junji Tomita, Kyosuke Nishida, Kosuke Nishida, Saito Itsumi, Hisako Asano, Masaaki Nagata, Otsuka Atsushi
Publikováno v:
ACL (1)
Question answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with evidence sente
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2614123a2b54e966db373fb521eafc14
Autor:
Kosuke Nishida, Junji Tomita, Kyosuke Nishida, Saito Itsumi, Hisako Asano, Kazutoshi Shinoda, Otsuka Atsushi
Publikováno v:
ACL (1)
This study tackles generative reading comprehension (RC), which consists of answering questions based on textual evidence and natural language generation (NLG). We propose a multi-style abstractive summarization model for question answering, called M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ec445e82f687e2d7fd8f190f4921926