Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Dirk Väth"'
Publikováno v:
Computers & Graphics. 103:45-60
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bdf71b2f4d75548277fb2ccf6e9176d9
https://doi.org/10.1016/j.cag.2021.12.003
https://doi.org/10.1016/j.cag.2021.12.003
Publikováno v:
Proceedings of the 25th Conference on Computational Natural Language Learning.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8821546889c1a5665b605d0493aaab31
https://doi.org/10.18653/v1/2021.conll-1.4
https://doi.org/10.18653/v1/2021.conll-1.4
Autor:
Zorica Kacarevic, Michael Neumann, Daniel Ortega, Maximilian Schmidt, Chia-Yu Li, Sabrina Jenne, Lindsey Vanderlyn, Moritz Völkel, Florian Lux, Dirk Väth, Ngoc Thang Vu, Pavel Denisov
Publikováno v:
ACL (demo)
We present ADVISER - an open-source, multi-domain dialog system toolkit that enables the development of multi-modal (incorporating speech, text and vision), socially-engaged (e.g. emotion recognition, engagement level prediction and backchanneling) c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70735790a1700dd9e836541b130259fe
http://arxiv.org/abs/2005.01777
http://arxiv.org/abs/2005.01777
Autor:
Daniel Ortega, Maximilian Schmidt, Ngoc Thang Vu, Dirk Väth, Zorica Karacevic, Moritz Völkel, Gianna Weber, Lindsey Vanderlyn
Publikováno v:
ACL (3)
In this paper, we present ADVISER - an open source dialog system framework for education and research purposes. This system supports multi-domain task-oriented conversations in two languages. It additionally provides a flexible architecture in which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::14fd70bcee3b12470b3ccf9961cbcba3
https://doi.org/10.18653/v1/p19-3016
https://doi.org/10.18653/v1/p19-3016
Autor:
Dirk Väth, Ngoc Thang Vu
Publikováno v:
SIGdial
In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7c5c1540ba78fe54dfdfd25914a40b9f
https://doi.org/10.18653/v1/w19-5908
https://doi.org/10.18653/v1/w19-5908