D
Da Ju
Researcher at Facebook
Publications - 18
Citations - 1145
Da Ju is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Set (psychology). The author has an hindex of 7, co-authored 15 publications receiving 360 citations.
Papers
More filters
Posted Content
Recipes for building an open-domain chatbot
Stephen Roller,Emily Dinan,Naman Goyal,Da Ju,Mary Williamson,Yinhan Liu,Jing Xu,Myle Ott,Kurt Shuster,Eric Michael Smith,Y-Lan Boureau,Jason Weston +11 more
TL;DR: Human evaluations show the best models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements, and the limitations of this work are discussed by analyzing failure cases of the models.
Posted Content
Recipes for Safety in Open-domain Chatbots.
TL;DR: A new human-and-model-in-the-loop framework for both training safer models and for evaluating them, as well as a novel method to distill safety considerations inside generative models without the use of an external classifier at deployment time are introduced.
Proceedings ArticleDOI
Recipes for building an open-domain chatbot
Stephen Roller,Emily Dinan,Naman Goyal,Da Ju,Mary Williamson,Yinhan Liu,Jing Xu,Myle Ott,Eric Michael Smith,Y-Lan Boureau,Jason Weston +10 more
TL;DR: The authors show that large scale models can learn these skills when given appropriate training data and choice of generation strategy, and build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make their models and code publicly available.
Journal ArticleDOI
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Kurt Shuster,Jing Xu,Mojtaba Komeili,Da Ju,Eric A. Smith,Stephen Roller,Megan Ung,Moya Chen,Kushal B. Arora,Joshua Lane,Morteza Behrooz,W.K.F. Ngan,Spencer Poff,Naman Goyal,Arthur Szlam,Y-Lan Boureau,Melanie Rae Kambadur,Jason Weston +17 more
TL;DR: The goal of this research program is to enable the community to study ever-improving responsible agents that learn through interaction in BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory.
Proceedings ArticleDOI
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
TL;DR: D dodecaDialogue is introduced, a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, and that the multi-tasking in general provides gains to both text and image-based tasks using several metrics in both the fine-tune and task transfer settings.