501 citations
- T. Ransford15 · h 26
- P. Mathieu14 · h 31
- A. Chbihi2 profiles13 · h 32
- E. Rosato2 profiles13 · h 34
- G. Joncas3 profiles13 · h 29
- M. Pârlog2 profiles13 · h 29
- B. Borderie2 profiles12 · h 39
- E. Galichet2 profiles12 · h 26
- L. Drissen12 · h 32
- M. Vigilante2 profiles12 · h 29
- R. Bougault2 profiles12 · h 33
- R. Roy3 profiles12 · h 19
- Centre for Research in Astrophysics of QuébecCA41 papers
- Centre National de la Recherche ScientifiqueFR37 papers
- Université de MontréalCA19 papers
- Canadian Institute for Theoretical AstrophysicsCA16 papers
- University of TorontoCA16 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR14 papers
- Grand Accélérateur National d'Ions LourdsFR13 papers
- European Southern ObservatoryCL12 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di NapoliIT12 papers
- Max Planck Institute for AstronomyDE12 papers
- CEA Paris-SaclayFR11 papers
- Herzberg Institute of AstrophysicsCA11 papers
18 papers · 1 filter
Attending Form and Context to Generate Specialized Out-of-VocabularyWords Representations
Nicolas Garneau, Jean-Samuel Leboeuf, Yuval Pinter +1
We propose a new contextual-compositional neural network layer that handles out-of-vocabulary (OOV) words in natural language processing (NLP) tagging tasks. This layer consists of…
A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well
Nicolas Garneau, Mathieu Godbout, David Beauchemin +2
In this paper, we reproduce the experiments of Artetxe et al. (2018b) regarding the robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. We…
A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift
Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calib…
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui, Fan Zhou, Christian Gagné +1
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights fr…
Towards Neural Language Evaluators
Hassan Kané, Yusuf Kocyigit, Pelkins Ajanoh +2
We review three limitations of BLEU and ROUGE -- the most popular metrics used to assess reference summaries against hypothesis summaries, come up with criteria for what a good met…
Erbium-doped aluminophosphosilicate all-fiber laser operating at 1584 nm
Marie-Pier Lord, Lauris Talbot, Olivier Boily +8
We report on an ytterbium-free erbium-doped aluminophosphosilicate all-fiber laser, producing an output power of 25 W at a wavelength of 1584 nm with a slope efficiency of 30% with…