164 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- J. Darmont2 profiles17 · h 23
- Julien Velcin2 profiles9 · h 13
- Cécile Favre2 profiles5 · h 14
- Sabine Loudcher2 profiles5 · h 14
- Pegdwendé N. Sawadogo2 profiles4 · h 4
- Adrien Guille3 · h 10
- F. Ravat3 · h 20
- Gael Poux-Medard3 · h 6
- Guillaume Metzler2 profiles3 · h 2
- Irina Proskurina3 · h 4
- J. Jacques3 · h 19
- O. Teste3 · h 25
- Université Lumière Lyon 2FR21 papers
- Seattle Epidemiologic Information and Research CenterUS12 papers
- Lyon 1 UniversitéFR10 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- Université de LyonFR4 papers
- Université Toulouse III - Paul SabatierFR4 papers
- Institut de Recherche en Informatique de ToulouseFR3 papers
- Institut Polytechnique de BordeauxFR3 papers
- Laboratoire d'Informatique en Images et Systèmes d'InformationFR3 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR3 papers
- Université Pierre Mendès FranceFR3 papers
- Université Toulouse-I-CapitoleFR3 papers
4 papers · 1 filter
Natural Language Querying System Through Entity Enrichment
Joshua Amavi, Mirian Halfeld Ferrari, Nicolas Hiot
This paper focuses on a domain expert querying system over databases. It presents a solution designed for a French enterprise interested in offering a natural language interface fo…
When Quantization Affects Confidence of Large Language Models?
Irina Proskurina, Luc Brun, Guillaume Metzler +1
Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation. Although quantized weig…
Mini Minds: Exploring Bebeshka and Zlata Baby Models
Irina Proskurina, Guillaume Metzler, Julien Velcin
In this paper, we describe the University of Lyon 2 submission to the Strict-Small track of the BabyLM competition. The shared task is created with an emphasis on small-scale langu…
Can BERT eat RuCoLA? Topological Data Analysis to Explain
Irina Proskurina, Irina Piontkovskaya, Ekaterina Artemova
This paper investigates how Transformer language models (LMs) fine-tuned for acceptability classification capture linguistic features. Our approach uses the best practices of topol…