no code implementations • WS 2019 • Maximin Coavoux, Hady Elsahar, Matthias Gall{\'e}
User-generated reviews of products or services provide valuable information to customers.
no code implementations • WS 2019 • Pierre Daix-Moreux, Matthias Gall{\'e}
Word embeddings continue to be of great use for NLP researchers and practitioners due to their training speed and easiness of use and distribution.
no code implementations • IJCNLP 2019 • Matthias Gall{\'e}
Byte-Pair Encoding (BPE) is an unsupervised sub-word tokenization technique, commonly used in neural machine translation and other NLP tasks.
no code implementations • IJCNLP 2019 • Hady Elsahar, Matthias Gall{\'e}
In this paper, we study the problem of predicting the performance drop of modern NLP models under domain-shift, in the absence of any target domain labels.
no code implementations • EMNLP 2020 • Jerin Philip, Alexandre Berard, Matthias Gall{\'e}, Laurent Besacier
We propose a novel adapter layer formalism for adapting multilingual models.