Showing 2024Show all
3 papers · 1 filter
cs.DL2024
ACL-rlg: A Dataset for Reading List Generation
Julien Aubert-Béduchaud, Florian Boudin, Béatrice Daille +1
Familiarizing oneself with a new scientific field and its existing literature can be daunting due to the large amount of available articles. Curated lists of academic references, o…
cs.CL2024
Self-Compositional Data Augmentation for Scientific Keyphrase Generation
Mael Houbre, Florian Boudin, Beatrice Daille +1
State-of-the-art models for keyphrase generation require large amounts of training data to achieve good performance. However, obtaining keyphrase-labeled documents can be challengi…
cs.CL2024
How Important Is Tokenization in French Medical Masked Language Models?
Yanis Labrak, Adrien Bazoge, Beatrice Daille +2
Subword tokenization has become the prevailing standard in the field of natural language processing (NLP) over recent years, primarily due to the widespread utilization of pre-trai…