• Publications
  • Influence
Neural Architectures for Named Entity Recognition
TLDR
We present neural architectures for NER that provide the best NER results ever reported in standard evaluation settings, even compared with models that use external resources, such as gazetteers. Expand
Word Translation Without Parallel Data
TLDR
We show that we can build a bilingual dictionary between two languages without using parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Expand
Cross-lingual Language Model Pretraining
TLDR
We propose two methods to learn cross-lingual language models (XLMs): one unsupervised that only relies on monolingual data, and one supervised that leverages parallel data with a new cross language model objective. Expand
Unsupervised Machine Translation Using Monolingual Corpora Only
TLDR
We propose a model that takes sentences from monolingual corpora in two languages and maps them into the same latent space, the model effectively learns to translate without using any labeled data. Expand
XNLI: Evaluating Cross-lingual Sentence Representations
TLDR
We extend the Multi-Genre Natural Language Inference Corpus (MultiNLI) to 14 languages, including low-resource languages such as Swahili and Urdu. Expand
Phrase-Based & Neural Unsupervised Machine Translation
TLDR
We propose two model variants, a neural and a phrase-based model. Expand
What you can cram into a single vector: Probing sentence embeddings for linguistic properties
TLDR
We introduce 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both Encoders and training methods. Expand
Fader Networks: Manipulating Images by Sliding Attributes
TLDR
This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. Expand
Massively Multilingual Word Embeddings
TLDR
We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Expand
Playing FPS Games with Deep Reinforcement Learning
TLDR
In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Expand
...
1
2
3
...