French Language Understanding via Bidirectional Encoder Representations from Transformers

Year: 2,020
Journal: Language Resources and Evaluation Conference
Languages: French
Programming languages: Python
Input data:

concatenation of two segments (sequences of tokens)
Segments usually consist of more than one natural sentence. The two segments are presented as a single input sequence to (FlauBERT) with special tokens delimiting them (s. BERT)
-> pair of sentences

Output data:

output representation depends on the entire input sequence (e.g. each token instance has a vector representation that depends on its left and right context)

In this paper, we introduce and share FlauBERT, a model learned on a very large and heterogeneous French corpus. Models of different sizes are trained using the new CNRS (French National Centre for Scientific Research) Jean Zay supercomputer. We apply our French language models to diverse NLP tasks (text classification, paraphrasing, natural language inference, parsing, word sense disambiguation) and show that most of the time they outperform other pre-training approaches.

Sign In


Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.