activity
20122022
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 4k across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2020

Evaluating Online Continual Learning with CALM

Germán Kruszewski, Ionut-Teodor Sorodoc, Tomas Mikolov

Online Continual Learning (OCL) studies learning over a continuous data stream without observing any single example more than once, a setting that is closer to the experience of hu…

cs.CL20198 cited

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…

cs.CL2018

Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

Armand Joulin, Piotr Bojanowski, Tomas Mikolov +2

Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space. Existing works typically solve a le…

cs.CL2018

Learning Word Vectors for 157 Languages

Edouard Grave, Piotr Bojanowski, Prakhar Gupta +2

Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredien…

cs.CL2018

Efficient Large-Scale Multi-Modal Classification

D. Kiela, E. Grave, A. Joulin +1

While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality i…

cs.CL2017

Advances in Pre-Training Distributed Word Representations

Tomas Mikolov, Edouard Grave, Piotr Bojanowski +2

Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl.…