Stephen is a Research Engineer at Facebook AI Research. His research interests include natural language processing, deep learning, language generation, conversational agents, and textual inference. Prior to FAIR, Stephen studied for his Ph.D. in natural language processing at UT Austin and was affiliated with the UTCS Machine Learning lab.
July 28, 2019
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 evaluated via human judgments of overall quality, the…
Abigail See, Stephen Roller, Douwe Kiela, Jason Weston,
July 28, 2019
July 28, 2019
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 approach allows us to set appropriate constraints for inferring…
Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela, Maximilian Nickel,
July 28, 2019
July 16, 2018
Methods for unsupervised hypernym detection may broadly be categorized according to two paradigms: pattern-based and distributional methods. In this paper, we study the performance of both approaches on several hypernymy tasks and find that…
Stephen Roller, Douwe Kiela, Maximilian Nickel,
July 16, 2018