no code implementations • 23 Apr 2024 • Julien Delaunay, Luis Galárraga, Christine Largouët
Most methods find those explanations by iteratively perturbing the target document until it is classified differently by the black box.
no code implementations • 16 Feb 2024 • Julien Delaunay
The primary goal is to develop methods for generating explanations for any model while ensuring that these explanations remain faithful to the underlying model and comprehensible to the users.
no code implementations • 27 Oct 2023 • Antoine Chaffin, Julien Delaunay
Because it does not rely on initial samples, it allows to generate explanations even when data is absent (e. g., for confidentiality reasons).
no code implementations • 28 Sep 2023 • Julien Delaunay, Hanh Thi Hong Tran, Carlos-Emiliano González-Gallardo, Georgeta Bordea, Nicolas Sidere, Antoine Doucet
Document-level relation extraction (DocRE) is an active area of research in natural language processing (NLP) concerned with identifying and extracting relationships between entities beyond sentence boundaries.
no code implementations • 2 Aug 2022 • Romaric Gaudel, Luis Galárraga, Julien Delaunay, Laurence Rozé, Vaishnavi Bhargava
The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models.
no code implementations • 4 Nov 2019 • Luis Galárraga, Julien Delaunay, Jean-Louis Dessalles
A referring expression (RE) is a description that identifies a set of instances unambiguously.