1

BERTrade: Using Contextual Embeddings to Parse Old French

We consider several neural language models, some of which trained or fine-tuned on a new corpus of raw Old and Middle French texts, and use their internal representations of words as inputs to train taggers and parsers on the SRCMF treebank.

Loïc Grobol, Mathilde Regnault, Pedro Ortiz Suarez, Benoît Sagot, Laurent Romary, Benoît Crabbé

BERTrade: Using Contextual Embeddings to Parse Old French

Challenges of language change and variation: towards an extended treebank of Medieval French

First steps of adapting a metagrammar for Contemporary French, FRMG, to Old French

Mathilde Regnault, Sophie Prévost, Eric Villemonte de la Clergerie

Adaptation d'une métagrammaire du français contemporain au français médiéval

First steps of adapting a metagrammar for Contemporary French, FRMG, to Old French (French version for a conference for young researchers)

Mathilde Regnault

Vers l'annotation par le jeu de corpus (plus) complexes : le cas de la langue de spécialité

We created a new scientific corpus for the GWAP Zombilingo.

Karën Fort, Bruno Guillaume, Nicolas Lefèbvre, Laura Ramírez, Mathilde Regnault, Mary Collins, Oksana Gavrilova, Tanti Kristanti