activity
20182022
most citedNeural Text Generation with Unlikelihood Training

241 citations · 395 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL202220 cited

Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion

Kurt Shuster, Mojtaba Komeili, Leonard Adolphs +3

Language models (LMs) have recently been shown to generate more factual responses by employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021).…

cs.CL20224 cited

Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents

Eric Michael Smith, Orion Hsu, Rebecca Qian +3

At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023),…

cs.CL20214 cited

Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue

Moya Chen, Paul A. Crook, Stephen Roller

We demonstrate that large language models are able to simulate Task Oriented Dialogues in novel domains, provided only with an API implementation and a list of goals. We show these…

cs.CL202042 cited

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…

cs.CL2019

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…

cs.CL2019

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…