Guillaume Le Berre — accepted AI-conference papers

2024

EUROPA: A Legal Multilingual Keyphrase Generation Dataset

Olivier Salaün, Frédéric Piedboeuf, Guillaume Le Berre, David Alfonso-Hermelo, Philippe Langlais

ACL 2024long

Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a novel dataset for multilingual keyphrase generation in the legal domain. It is derived from le…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2022

Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning

Guillaume Le Berre, Christophe Cerisara, Philippe Langlais, Guy Lapalme

ACL 2022short

Pre-trained models have shown very good performances on a number of question answering benchmarks especially when fine-tuned on multiple question answering datasets at once. In this work, we propose an approach for generating a fine-tuning dataset thanks to a rule-based algorithm that generates ques…

Cited by 16 Source ↗PDF ↗Scholar ↗