241 citations · 311 across the 3 of their papers we have counts for
6 papers
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
Stephen Roller, Y-Lan Boureau, Jason Weston +13
We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been bui…
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Margaret Li, Stephen Roller, Ilia Kulikov +4
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely to…
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
Kurt Shuster, Da Ju, Stephen Roller +3
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by u…
Neural Text Generation with Unlikelihood Training
Sean Welleck, Ilia Kulikov, Stephen Roller +3
Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and de…
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
Matt Le, Stephen Roller, Laetitia Papaxanthos +2
We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This ap…
What makes a good conversation? How controllable attributes affect human judgments
Abigail See, Stephen Roller, Douwe Kiela +1
A good conversation requires balance -- between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly…