Eric Michael Smith

Eric is a Research Engineer at Facebook AI Research (FAIR). Prior to FAIR, he was a machine learning engineer at Blue Apron, where he created and maintained the company forecast of the relative order volume of upcoming product offerings. Eric was a fellow of Insight Data Science in New York and holds a doctorate in physics from Princeton University for his biophysics research in measuring protein and mRNA expression in the developing fruit fly embryo with high spatiotemporal resolution.

Eric's Publications

July 29, 2019

RESEARCH

Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset

One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to recognize and acknowledge others’ feelings in a conversation,…

Hannah Rashkin, Eric Michael Smith, Margaret Li, Y-Lan Boureau,

July 29, 2019

May 06, 2019

RESEARCH

SPEECH & AUDIO

Multiple-Attribute Text Rewriting

The dominant approach to unsupervised “style transfer” in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its “style”. In this paper, we show that this condition is not necessary…

Guillaume Lample, Sandeep Subramanian, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, Y-Lan Boureau,

May 06, 2019