Human-centric dialog training via offline reinforcement learning
Main Authors: | Jaques, Natasha, Shen, Judy Hanwen, Ghandeharioun, Asma, Ferguson, Craig, Lapedriza, Agata, Jones, Noah, Gu, Shixiang, Picard, Rosalind W. |
---|---|
Other Authors: | Program in Media Arts and Sciences (Massachusetts Institute of Technology) |
Format: | Article |
Language: | English |
Published: |
Association for Computational Linguistics (ACL)
2022
|
Online Access: | https://hdl.handle.net/1721.1/146608 |
Similar Items
-
Approximating interactive human evaluation with self-play for open-domain dialog systems
by: Ghandeharioun, Asma, et al.
Published: (2022) -
Hierarchical Reinforcement Learning for Open-Domain Dialog
by: Saleh, Abdelrhman, et al.
Published: (2022) -
Approximating interactive human evaluation with self-play for open-domain dialog systems
by: Ghandeharioun, A, et al.
Published: (2021) -
Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias
by: Picard, Rosalind W., et al.
Published: (2021) -
Predicting students' happiness from physiology, phone, mobility, and behavioral data
by: Jaques, Natasha Mary, et al.
Published: (2017)