Alexis Conneau

Alexis Conneau is a research scientist at Facebook AI in Menlo Park, who completed his PhD at FAIR Paris in 2019. He previously graduated from École Polytechnique in Mathematics. His research revolves around unsupervised representation learning, transfer learning for NLU and cross-lingual understanding. His past work in these areas includes InferSent, MUSE, XNLI, XLM and XLM-R. Alexis published articles in the main NLP and machine learning conferences including ACL, EMNLP, ICLR and NeurIPS. He received an Outstanding Paper Award at EMNLP 2017, and was a co-author of the EMNLP 2018 Best Paper Award.

Alexis' Publications

May 27, 2020

RESEARCH

Phrase-Based & Neural Unsupervised Machine Translation

Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of bitexts, which hinders…

Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato

May 27, 2020

May 27, 2020

RESEARCH

XNLI: Evaluating Cross-lingual Sentence Representations

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models…

Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel R. Bowman, Holger Schwenk, Ves Stoyanov

May 27, 2020

May 27, 2020

RESEARCH

What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties

Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing…

Alexis Conneau, Germán Kruszewski, Guillaume Lample, LoÏc Barrault, Marco Baroni

May 27, 2020

May 27, 2020

RESEARCH

COMPUTER VISION

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough…

Alexis Conneau, Douwe Kiela, Holger Schwenk, LoÏc Barrault, Antoine Bordes

May 27, 2020

May 27, 2020

RESEARCH

COMPUTER VISION

Word Translation Without Parallel Data

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 data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts…

Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

May 27, 2020

May 27, 2020

RESEARCH

NLP

Unsupervised Machine Translation Using Monolingual Corpora Only

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource language pairs, yet requiring tens of thousands of parallel sentences. In this work, we take this research…

Guillaume Lample, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato

May 27, 2020