no code implementations • VarDial (COLING) 2020 • Gabriel Bernier-Colborne, Cyril Goutte
We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2020 VarDial evaluation campaign.
no code implementations • EACL (VarDial) 2021 • Gabriel Bernier-Colborne, Serge Leger, Cyril Goutte
We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign.
no code implementations • VarDial (COLING) 2022 • Gabriel Bernier-Colborne, Serge Leger, Cyril Goutte
We describe the systems developed by the National Research Council Canada for the French Cross-Domain Dialect Identification shared task at the 2022 VarDial evaluation campaign.
no code implementations • AMTA 2022 • Shivendra Bhardwa, David Alfonso-Hermelo, Philippe Langlais, Gabriel Bernier-Colborne, Cyril Goutte, Michel Simard
While recent studies have been dedicated to cleaning very noisy parallel corpora to improve Machine Translation training, we focus in this work on filtering a large and mostly clean Translation Memory.
no code implementations • COLING 2020 • Shivendra Bhardwaj, David Alfonso Hermelo, Phillippe Langlais, Gabriel Bernier-Colborne, Cyril Goutte, Michel Simard
Deep neural models tremendously improved machine translation.
no code implementations • LREC 2020 • Gabriel Bernier-Colborne, Phillippe Langlais
To assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or ambiguity.
no code implementations • WS 2019 • Gabriel Bernier-Colborne, Chi-kiu Lo
We describe the National Research Council Canada team{'}s submissions to the parallel corpus filtering task at the Fourth Conference on Machine Translation.
no code implementations • WS 2019 • Gabriel Bernier-Colborne, Cyril Goutte, Serge L{\'e}ger
We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign.
1 code implementation • SEMEVAL 2018 • Gabriel Bernier-Colborne, Caroline Barri{\`e}re
This report describes the system developed by the CRIM team for the hypernym discovery task at SemEval 2018.
Ranked #1 on Hypernym Discovery on General
no code implementations • WS 2016 • Gabriel Bernier-Colborne, Patrick Drouin
We investigate how both model-related factors and application-related factors affect the accuracy of distributional semantic models (DSMs) in the context of specialized lexicography, and how these factors interact.
no code implementations • JEPTALNRECITAL 2016 • Gabriel Bernier-Colborne, Patrick Drouin
Nous utilisons des mod{\`e}les s{\'e}mantiques distributionnels pour d{\'e}tecter des termes qui {\'e}voquent le m{\^e}me cadre s{\'e}mantique.
no code implementations • JEPTALNRECITAL 2016 • Gabriel Bernier-Colborne, Patrick Drouin
Nous {\'e}valuons deux mod{\`e}les s{\'e}mantiques distributionnels au moyen d{'}un jeu de donn{\'e}es repr{\'e}sentant quatre types de relations lexicales et analysons l{'}influence des param{\`e}tres des deux mod{\`e}les.
no code implementations • JEPTALNRECITAL 2015 • Fran{\c{c}}ois Lareau, Gabriel Bernier-Colborne, Patrick Drouin
En s{\'e}mantique distributionnelle, le sens des mots est mod{\'e}lis{\'e} par des vecteurs qui repr{\'e}sentent leur distribution en corpus.
no code implementations • JEPTALNRECITAL 2015 • Gabriel Bernier-Colborne
Dans cet article, nous montrons qu{'}un graphe {\`a} 1 plus proche voisin (graphe 1-PPV) offre diff{\'e}rents moyens d{'}explorer les voisinages s{\'e}mantiques capt{\'e}s par un mod{\`e}le distributionnel.