Recent studies have demonstrated the efficiency of generative pretraining for English
natural language understanding. In this work, we extend this approach to multiple …

Recent studies have demonstrated the efficiency of generative pretraining for English
natural language understanding. In this work, we extend this approach to multiple …

We introduce an architecture to learn joint multilingual sentence representations for 93
languages, belonging to more than 30 different families and written in 28 different scripts …

Semantic representation is receiving growing attention in NLP in the past few years, and
many proposals for semantic schemes (eg, AMR, UCCA, GMB, UDS) have been put forth …

State-of-the-art natural language processing systems rely on supervision in the form of
annotated data to learn competent models. These models are generally trained on data in a …

State-of-the-art methods for learning cross-lingual word embeddings have relied on
bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel …

State-of-the-art methods for learning cross-lingual word embeddings have relied on
bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel …

Cross-lingual representations of words enable us to reason about word meaning in
multilingual contexts and are a key facilitator of cross-lingual transfer when developing …

Over the last two decades, determining the similarity between words as well as between
their meanings, that is, word senses, has been proven to be of vital importance in the field of …

Usually bilingual word vectors are trained" online". Mikolov et al. showed they can also be
found" offline", whereby two pre-trained embeddings are aligned with a linear …