• Publications
  • Influence
Enriching Word Vectors with Subword Information
TLDR
We propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams, and represent words as the sum of then-gram vectors. Expand
  • 4,732
  • 726
  • PDF
Bag of Tricks for Efficient Text Classification
TLDR
This paper explores a simple and efficient baseline for text classification. Expand
  • 2,316
  • 284
  • PDF
Deep Clustering for Unsupervised Learning of Visual Features
TLDR
We present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features and uses the subsequent assignments as supervision to update the weights of the network. Expand
  • 678
  • 103
  • PDF
Learning Word Vectors for 157 Languages
TLDR
We train high quality word vectors trained on Wikipedia and the Common Crawl, as well as three new word analogy datasets to evaluate these word vectors. Expand
  • 635
  • 87
  • PDF
Discriminative clustering for image co-segmentation
TLDR
We combine existing tools for bottom-up image segmentation such as normalized cuts, with kernel methods commonly used in object recognition. Expand
  • 445
  • 81
  • PDF
Unsupervised Joint Object Discovery and Segmentation in Internet Images
TLDR
We present a new unsupervised algorithm to discover and segment out common objects from large and diverse image collections. Expand
  • 316
  • 76
  • PDF
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
TLDR
We introduce a model for bidirectional retrieval of images and sentences through a deep, multi-modal embedding of visual and natural language data. Expand
  • 648
  • 62
  • PDF
Advances in Pre-Training Distributed Word Representations
TLDR
We show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. Expand
  • 584
  • 51
  • PDF
Multi-class cosegmentation
TLDR
This paper proposes a novel energy-minimization approach to cosegmentation that can handle multiple classes and a significantly larger number of images. Expand
  • 277
  • 51
  • PDF
FastText.zip: Compressing text classification models
TLDR
We propose a text classifier, derived from the fastText approach, which at test time requires only a fraction of the memory compared to the original one, without noticeably sacrificing accuracy. Expand
  • 409
  • 50
  • PDF
...
1
2
3
4
5
...