Roles and responsibilities
I am a research officer in the Multilingual Text Processing team at the Digital Technologies Research Centre (DT), National Research Council of Canada (NRC-CNRC).
Current research and/or projects
My current research work centers on machine translation (MT). For the past several years, I have been project leader for NRC’s collaborations with the Canadian government’s Translation Bureau. Recently, I am also interested in text readability: automatic readability assessment and text simplification.
Research and/or project statements
- Automatic and Computer-assisted Translation. This includes: training high-quality neural machine translation (NMT) systems to support professional translators; estimating the quality of MT output and highlighting potential errors (“MT quality estimation”) and exploiting translator feedback to improve quality (“continual learning”).
- Parallel Corpus Filtering. Creating high-quality training data for MT and other multilingual applications.
Education
- PhD in Computer Science, Université de Montréal, 2005.
- MSc in Computer Science, McGill University, 1990.
- BSc in Mathematics and Computer Science, Université de Montréal, 1986.
Professional activities/interests
- Research Director, Association for Machine Translation in the Americas (AMTA), 2012-2016
- Program Chair at the 2014 Conference of the Association for Machine Translation in the Americas (AMTA 2014)
- Area co-chair in Multilinguality at the 2011 Annual Meeting of the Association for Computational Linguistics (ACL 2011)
Affiliations
- Association for Computational Linguistics
- Association for Machine Translation in the Americas
Key publications
A more completed list is available on Google Scholar
- Larkin, Samuel, Michel Simard, and Rebecca Knowles (2021). "Like Chalk and Cheese? On the Effects of Translationese in MT Training." Proceedings of the 18th Biennial Machine Translation Summit (Volume 1: Research Track).
- Lo, Chi-kiu, and Michel Simard (2019). "Fully unsupervised crosslingual semantic textual similarity metric based on BERT for identifying parallel data." Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL).
- Littell, Patrick, Samuel Larkin, Darlene Stewart, Michel Simard, Cyril Goutte, and Chi-kiu Lo (2018). "Measuring sentence parallelism using Mahalanobis distances: The NRC unsupervised submissions to the WMT18 Parallel Corpus Filtering shared task." In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 900-907.
Previous work experience
2003–2005
Xerox Research Centre Europe (XRCE), Grenoble, France.
Postdoctoral Researcher
1996–2003
RALI Laboratory, Université de Montréal, Montreal QC.
Research Scientist
1989–1996
Centre for Information Technologies Innovation (CITI), Industry Canada, Laval QC.
Computer Scientist.
