F
François Yvon
Researcher at Université Paris-Saclay
Publications - 236
Citations - 4223
François Yvon is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: Machine translation & Language model. The author has an hindex of 31, co-authored 222 publications receiving 3966 citations. Previous affiliations of François Yvon include Télécom ParisTech & University of Paris-Sud.
Papers
More filters
Proceedings Article
Practical Very Large Scale CRFs
TL;DR: This paper addresses the issue of training very large CRFs, containing up to hundreds output labels and several billion features, and indicates that efficiency stems here from the sparsity induced by the use of a l penalty term.
Proceedings ArticleDOI
Normalizing SMS: are Two Metaphors Better than One ?
TL;DR: This paper presents an comparative study of systems aiming at normalizing the orthography of French SMS messages, one drawing inspiration from the Machine Translation task; the other using techniques that are commonly used in automatic speech recognition devices.
Proceedings ArticleDOI
Structured Output Layer neural network language model
TL;DR: A new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM, able to handle vocabularies of arbitrary size, hence dispensing with the design of short-lists that are commonly used in NNLMs.
Proceedings Article
Continuous Space Translation Models with Neural Networks
TL;DR: Several continuous space translation models are explored, where translation probabilities are estimated using a continuous representation of translation units in lieu of standard discrete representations, jointly computed using a multi-layer neural network with a SOUL architecture.
Proceedings ArticleDOI
Text segmentation via topic modeling: an analytical study
TL;DR: The use of latent Dirichlet allocation (LDA) topic model to segment a text into semantically coherent segments is investigated and yields significantly better performance than most of the available unsupervised methods on a benchmark dataset.