Ludovic Denoyer
Ludovic is a Research Scientist at FAIR, mainly focusing on various machine learning problems, particularly on reinforcement learning and human-machine interaction. He was previously a professor at Sorbonne Universités.
Ludovic's Publications
July 27, 2019
RESEARCH
INTEGRITY
Unsupervised Question Answering by Cloze Translation
Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is…
Patrick Lewis, Ludovic Denoyer, Sebastian Riedel,
July 27, 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
March 11, 2019
RESEARCH
SPEECH & AUDIO
Stochastic Adaptive Neural Architecture Search for Keyword Spotting
The problem of keyword spotting i.e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows. Due to the difficulty of the task, baseline models are usually large, resulting…
Tom Véniat, Olivier Schwander, Ludovic Denoyer,
March 11, 2019
