RESEARCH AREA
Conversational AI
Conversational systems are becoming an integral part of our daily routines. Every day, millions of people use natural-language interfaces via in-home devices, phones, or messaging channels such as Messenger. We strive to create new conversational technologies that have a deep understanding of the conversation and the context around it and deliver a personalized experience to the user that is both task oriented and empathic.
The next generation of conversational AI systems will be multi-modal and pro-active, integrating cues across several modalities to provide creative and on-spot response to the users.
Latest Publications
CONVERSATIONAL AI
Engaging Image Captioning via Personality
Standard image captioning tasks such as COCO and Flickr30k are factual, neutral in tone and (to a human) state the obvious (e.g., “a man playing a guitar”).
Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, Jason Weston
CONVERSATIONAL AI
What makes a good conversation? How controllable attributes affect human judgments
In this work, we examine two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chitchat dialogue: repetition, specificity, response-relatedness and question-asking.
Abigail See, Stephen Roller, Douwe Kiela, Jason Weston
