2k citations · 5.5k across the 40 of their papers we have counts for
4 papers · 1 filter
Updating Pre-trained Word Vectors and Text Classifiers using Monolingual Alignment
Piotr Bojanowski, Onur Celebi, Tomas Mikolov +2
In this paper, we focus on the problem of adapting word vector-based models to new textual data. Given a model pre-trained on large reference data, how can we adapt it to a smaller…
Misspelling Oblivious Word Embeddings
Bora Edizel, Aleksandra Piktus, Piotr Bojanowski +3
In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain…
Adaptive Attention Span in Transformers
Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski +1
We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while ma…
Unsupervised Pre-Training of Image Features on Non-Curated Data
Mathilde Caron, Piotr Bojanowski, Julien Mairal +1
Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervi…