Search Results for author: Gabriel Bernier-Colborne

Found 18 papers, 2 papers with code

N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021

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.

Language Identification

Refining an Almost Clean Translation Memory Helps Machine Translation

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.

Machine Translation Translation

Challenges in Neural Language Identification: NRC at VarDial 2020

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.

Language Identification

Transfer Learning Improves French Cross-Domain Dialect Identification: NRC @ VarDial 2022

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.

Dialect Identification Language Modelling +1

HardEval: Focusing on Challenging Tokens to Assess Robustness of NER

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.

NER

NRC Parallel Corpus Filtering System for WMT 2019

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.

Machine Translation Translation

Improving Cuneiform Language Identification with BERT

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.

Language Identification

Evaluation of distributional semantic models: a holistic approach

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.

\'Evaluation des mod\`eles s\'emantiques distributionnels : le cas de la d\'erivation syntaxique (Evaluation of distributional semantic models : The case of syntactic derivation )

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.

La s\'eparation des composantes lexicale et flexionnelle des vecteurs de mots

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.

Exploration de mod\`eles distributionnels au moyen de graphes 1-PPV

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.