4k citations · 13.4k across the 76 of their papers we have counts for
8 papers · 1 filter
Improving Neural Language Models with a Continuous Cache
Edouard Grave, Armand Joulin, Nicolas Usunier
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 sto…
FastText.zip: Compressing text classification models
Armand Joulin, Edouard Grave, Piotr Bojanowski +3
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutio…
Learning Visual N-Grams from Web Data
Ang Li, Allan Jabri, Armand Joulin +1
Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands…
Variable Computation in Recurrent Neural Networks
Yacine Jernite, Edouard Grave, Armand Joulin +1
Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through d…
Efficient softmax approximation for GPUs
Edouard Grave, Armand Joulin, Moustapha Cissé +2
We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the li…
Bag of Tricks for Efficient Text Classification
Armand Joulin, Edouard Grave, Piotr Bojanowski +1
This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifi…