A
Armand Joulin
Researcher at Facebook
Publications - 136
Citations - 36652
Armand Joulin is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Word (computer architecture). The author has an hindex of 55, co-authored 125 publications receiving 25130 citations. Previous affiliations of Armand Joulin include Microsoft & École Normale Supérieure.
Papers
More filters
Journal ArticleDOI
Enriching Word Vectors with Subword Information
TL;DR: This paper proposed a new approach based on skip-gram model, where each word is represented as a bag of character n-grams, words being represented as the sum of these representations, allowing to train models on large corpora quickly and allowing to compute word representations for words that did not appear in the training data.
Proceedings ArticleDOI
Bag of Tricks for Efficient Text Classification
TL;DR: FastText as mentioned in this paper explores a simple and efficient baseline for text classification, which is often on par with deep learning classifiers in terms of accuracy and many orders of magnitude faster for training and evaluation.
Posted Content
Enriching Word Vectors with Subword Information
TL;DR: A new approach based on the skipgram model, where each word is represented as a bag of character n-grams, with words being represented as the sum of these representations, which achieves state-of-the-art performance on word similarity and analogy tasks.
Posted Content
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
TL;DR: This paper proposes an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons, and uses a swapped prediction mechanism where it predicts the cluster assignment of a view from the representation of another view.
Posted Content
Deep Clustering for Unsupervised Learning of Visual Features
TL;DR: This work presents DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features and outperforms the current state of the art by a significant margin on all the standard benchmarks.