Holger Schwenk7 papers on this site (2015–2019)CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBHolger Schwenk, Guillaume Wenzek, Sergey Edunov, et al.2019Margin-based Parallel Corpus Mining with Multilingual Sentence EmbeddingsMikel Artetxe, Holger Schwenk2019MLQA: Evaluating Cross-lingual Extractive Question AnsweringPatrick Lewis, Barlas Oğuz, Ruty Rinott, et al.2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from WikipediaHolger Schwenk, Vishrav Chaudhary, Shuo Sun, et al.2019Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and BeyondMikel Artetxe, Holger Schwenk2018Supervised Learning of Universal Sentence Representations from Natural Language Inference DataAlexis Conneau, Douwe Kiela, Holger Schwenk, et al.2017On Using Monolingual Corpora in Neural Machine TranslationCaglar Gulcehre, Orhan Firat, Kelvin Xu, et al.2015