Many cognitive approaches to well-being, such as recognizing and reframi...
Publicly deploying research chatbots is a nuanced topic involving necess...
We present BlenderBot 3x, an update on the conversational model BlenderB...
The promise of interaction between intelligent conversational agents and...
Frozen models trained to mimic static datasets can never improve their
p...
We present BlenderBot 3, a 175B parameter dialogue model capable of
open...
At the heart of improving conversational AI is the open problem of how t...
Current open-domain conversational models can easily be made to talk in
...
Inspiration moves a person to see new possibilities and transforms the w...
Over the last several years, end-to-end neural conversational agents hav...
Open-domain dialogue agents have vastly improved, but still confidently
...
Models trained on large unlabeled corpora of human interactions will lea...
Open-domain conversation models have become good at generating
natural-s...
We present our view of what is necessary to build an engaging open-domai...
We investigate multi-scale transformer language models that learn
repres...
Building open-domain chatbots is a challenging area for machine learning...
Being engaging, knowledgeable, and empathetic are all desirable general
...
As single-task accuracy on individual language and image tasks has impro...
Text style transfer is usually performed using attributes that can take ...
Generative dialogue models currently suffer from a number of problems wh...
We introduce dodecaDialogue: a set of 12 tasks that measures if a
conver...
Traditional recommendation systems produce static rather than interactiv...
How do we know if communication is emerging in a multi-agent system? The...
The dominant approach to unsupervised "style transfer" in text is based ...
Beyond understanding what is being discussed, human communication requir...
Traditional dialog systems used in goal-oriented applications require a ...