Guillaume Lample

Guillaume joined Facebook AI Research as a resident PhD student in August 2016. He's advised by Marc’Aurelio Ranzato (Facebook) and Ludovic Denoyer (UPMC/LIP6). He also graduated from Carnegie Mellon University in 2016, where he was working under the supervision of Chris Dyer. Before that, Guillaume received a bachelor's and master's degree in mathematics from École Polytechnique.

Guillaume's Publications

October 31, 2019

RESEARCH

The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English

For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available…

Guillaume Lample, Francisco (Paco) Guzman, Peng-Jen Chen, Myle Ott, Juan Pino, Philipp Koehn, Vishrav Chaudhary, Marc'Aurelio Ranzato

October 31, 2019

May 06, 2019

RESEARCH

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"…

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

May 06, 2019

October 31, 2018

RESEARCH

Phrase-Based & Neural Unsupervised Machine Translation

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of bitexts, which hinders their applicability to the majority of language pairs…

Guillaume Lample, Myle Ott, Alexis Conneau, Marc'Aurelio Ranzato, Ludovic Denoyer

October 31, 2018