310 citations
- École Polytechnique Fédérale de LausanneCH87 papers
- Institut Denis PoissonFR42 papers
- Université de ToursFR37 papers
- Université d'OrléansFR37 papers
- Centre National de la Recherche ScientifiqueFR10 papers
- Brno University of TechnologyCZ7 papers
- CERMICSFR7 papers
- University of ManchesterGB7 papers
- Italian Institute of TechnologyIT6 papers
- Queen Mary University of LondonGB6 papers
- University of BernCH6 papers
- Institute for Scientific and Technological ResearchMX5 papers
8 papers · 1 filter
Simple Image Description Generator via a Linear Phrase-Based Approach
Remi Lebret, Pedro O. Pinheiro, Ronan Collobert
Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model…
Learning linearly separable features for speech recognition using convolutional neural networks
Dimitri Palaz, Mathew Magimai Doss, Ronan Collobert
Automatic speech recognition systems usually rely on spectral-based features, such as MFCC of PLP. These features are extracted based on prior knowledge such as, speech perception…
Joint RNN-Based Greedy Parsing and Word Composition
Joël Legrand, Ronan Collobert
This paper introduces a greedy parser based on neural networks, which leverages a new compositional sub-tree representation. The greedy parser and the compositional procedure are j…
N-gram-Based Low-Dimensional Representation for Document Classification
Rémi Lebret, Ronan Collobert
The bag-of-words (BOW) model is the common approach for classifying documents, where words are used as feature for training a classifier. This generally involves a huge number of f…
Rehabilitation of Count-based Models for Word Vector Representations
Rémi Lebret, Ronan Collobert
Recent works on word representations mostly rely on predictive models. Distributed word representations (aka word embeddings) are trained to optimally predict the contexts in which…
Fast Rates by Transferring from Auxiliary Hypotheses
Ilja Kuzborskij, Francesco Orabona
In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We foc…