Filter Results:
- Full text PDF available (52)
Publication Year
2004
2018
- This year (9)
- Last 5 years (41)
- Last 10 years (74)
Publication Type
Co-author
Journals and Conferences
Learn More
We consider the problem of embedding entities and relationships of multirelational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train,… (More)
- Jason Weston, Samy Bengio, Nicolas Usunier
- IJCAI
- 2011
Image annotation datasets are becoming larger and larger, with tens of millions of images and tens of thousands of possible annotations. We propose a strongly performing method that scales to such… (More)
- Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston
- ArXiv
- 2015
Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask… (More)
- Jason Weston, Samy Bengio, Nicolas Usunier
- Machine Learning
- 2010
Image annotation datasets are becoming larger and larger, with tens of millions of images and tens of thousands of possible annotations. We propose a strongly performing method that scales to such… (More)
We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1. Parseval networks… (More)
Learning from Multiple Partially Observed Views - an Application to Multilingual Text Categorization
- Massih-Reza Amini, Nicolas Usunier, Cyril Goutte
- NIPS
- 2009
We address the problem of learning classifiers when observat ions have multiple views, some of which may not be observed for all examples. We a ssume the existence of view generating functions which… (More)
- Edouard Grave, Armand Joulin, Nicolas Usunier
- ICLR
- 2017
We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden… (More)
- Antoine Bordes, Jason Weston, Nicolas Usunier
- ECML/PKDD
- 2014
Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to… (More)
This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the… (More)
- Nicolas Usunier, David Buffoni, Patrick Gallinari
- ICML
- 2009
In ranking with the pairwise classification approach, the loss associated to a predicted ranked list is the mean of the pairwise classification losses. This loss is inadequate for tasks like… (More)