no code implementations • 6 Apr 2022 • Louis Marceau, Raouf Belbahar, Marc Queudot, Nada Naji, Eric Charton, Marie-Jean Meurs
Acquiring training data to improve the robustness of dialog systems can be a painstakingly long process.
no code implementations • 28 Oct 2021 • Hadrien Lautraite, Nada Naji, Louis Marceau, Marc Queudot, Eric Charton
Clarification resolution plays an important role in various information retrieval tasks such as interactive question answering and conversational search.
no code implementations • JEPTALNRECITAL 2020 • Elham Mohammadi, Louis Marceau, Eric Charton, Leila Kosseim, Luka Nerima, Marie-Jean Meurs
Nous pr{\'e}sentons un mod{\`e}le d{'}apprentissage automatique qui combine mod{\`e}les neuronaux et linguistiques pour traiter les t{\^a}ches de classification dans lesquelles la distribution des {\'e}tiquettes des instances est d{\'e}s{\'e}quilibr{\'e}e. Les performances de ce mod{\`e}le sont mesur{\'e}es {\`a} l{'}aide d{'}exp{\'e}riences men{\'e}es sur les t{\^a}ches de classification de recettes de cuisine de la campagne DEFT 2013 (Grouin et al., 2013).
no code implementations • LREC 2020 • Elham Mohammadi, Nada Naji, Louis Marceau, Marc Queudot, Eric Charton, Leila Kosseim, Marie-Jean Meurs
In this paper, we propose a neural-based model to address the first task of the DEFT 2013 shared task, with the main challenge of a highly imbalanced dataset, using state-of-the-art embedding approaches and deep architectures.
no code implementations • 25 Jul 2019 • Louis Marceau, Lingling Qiu, Nick Vandewiele, Eric Charton
Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms.
no code implementations • LREC 2016 • Marie-Jean Meurs, Hayda Almeida, Ludovic Jean-Louis, Eric Charton
This paper presents SemLinker, an open source system that discovers named entities, connects them to a reference knowledge base, and clusters them semantically.
no code implementations • LREC 2014 • Eric Charton, Marie-Jean Meurs, Ludovic Jean-Louis, Michel Gagnon
The approach extends the surface form coverage of our entity linking system, and rewrites or reformulates misspelled mentions (entities) prior to starting the annotation process.
no code implementations • JEPTALNRECITAL 2013 • Eric Charton, Michel Gagnon, Ludovic Jean-Louis
no code implementations • LREC 2012 • Eric Charton, Michel Gagnon
The Semantic Annotation (SA) task consists in establishing the relation between a textual entity (word or group of words designating a named entity of the real world or a concept) and its corresponding entity in an ontology.