Cyril Goutte
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Cyril Goutte has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Eric Gaussier
4 shared publications- Lars Kai Hansen
Technical University of Denmark
4 shared publications Nicolas Usunier
3 shared publicationsSerge Léger
National Research Council Canada
3 shared publications- Egill Rostrup
Center for Neuropsychiatric Schizophrenia Research (CNSR) & Center for Clinical Intervention and Neuropsychiatric Schizophrenia Research (CINS), Mental Health Center Glostrup, Copenhagen University Hospital – Mental Health Services CPH
2 shared publications Guillaume Durand
National Research Council Canada
2 shared publications
Latest Publications
- 20 June 2018
- Published by Springer Nature
- p. 109-113
On the Learning Curve Attrition Bias in Additive Factor Modeling
- 20 June 2018
- Published by Springer Nature
- p. 109-113
On the Learning Curve Attrition Bias in Additive Factor Modeling
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Exploring Optimal Voting in Native Language Identification
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
Exploring Optimal Voting in Native Language Identification
- Open Access
- 1 January 2015
- Published by Association for Computational Linguistics (ACL)
- p. 75-80
Towards Automatic Description of Knowledge Components
- 1 January 2015
- Published by Association for Computational Linguistics (ACL)
- p. 75-80
Open AccessTowards Automatic Description of Knowledge Components
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 139-145
The NRC System for Discriminating Similar Languages
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 139-145
The NRC System for Discriminating Similar Languages
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 499-509
Linear Mixture Models for Robust Machine Translation
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 499-509
Linear Mixture Models for Robust Machine Translation
- Open Access
- 12 August 2012
- Published by Association for Computing Machinery (ACM)
- p. 1071-1072
Fast on-line learning for multilingual categorization
Multiview learning has been shown to be a natural and efficient framework for supervised or semi-supervised learning of multilingual document categorizers. The state-of-the-art co-regularization approach relies on alternate minimizations of a combination of language-specific categorization errors and a disagreement between the outputs of the monolingual text categorizers. This is typically solved by repeatedly training categorizers on each language with the appropriate regularizer. We extend and improve this approach by introducing an on-line learning scheme, where language-specific updates are interleaved in order to iteratively optimize the global cost in one pass. Our experimental results show that this produces similar performance as the batch approach, at a fraction of the computational cost.Peer reviewed: YesNRC publication: Ye
- 12 August 2012
- Published by Association for Computing Machinery (ACM)
- p. 1071-1072
Open AccessFast on-line learning for multilingual categorization
Multiview learning has been shown to be a natural and efficient framework for supervised or semi-supervised learning of multilingual document categorizers. The state-of-the-art co-regularization approach relies on alternate minimizations of a combination of language-specific categorization errors and a disagreement between the outputs of the monolingual text categorizers. This is typically solved by repeatedly training categorizers on each language with the appropriate regularizer. We extend and improve this approach by introducing an on-line learning scheme, where language-specific updates are interleaved in order to iteratively optimize the global cost in one pass. Our experimental results show that this produces similar performance as the batch approach, at a fraction of the computational cost.Peer reviewed: YesNRC publication: Ye
- 1 January 2011
- Published by Springer Nature
- p. 443-458
Multiview Semi-supervised Learning for Ranking Multilingual Documents
- 1 January 2011
- Published by Springer Nature
- p. 443-458
Multiview Semi-supervised Learning for Ranking Multilingual Documents
- Open Access
- 19 July 2010
- Published by Association for Computing Machinery (ACM)
- p. 475-482
Combining coregularization and consensus-based self-training for multilingual text categorization
International audienceWe investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the framework of multiview learning, where different languages correspond to different views of the same document, combined with semi-supervised learning in order to benefit from unlabeled documents. We rely on two techniques, coregularization and consensus-based self-training, that combine multiview and semi-supervised learning in different ways. Our approach trains different monolingual classifiers on each of the views, such that the classifiers' decisions over a set of unlabeled examples are in agreement as much as possible, and iteratively labels new examples from another unlabeled training set based on a consensus across language-specific classifiers. We derive a boosting-based training algorithm for this task, and analyze the impact of the number of views on the semi-supervised learning results on a multilingual extension of the Reuters RCV1/RCV2 corpus using five different languages. Our experiments show that coregularization and consensus-based self-training are complementary and that their combination is especially effective in the interesting and very common situation where there are few views (languages) and few labeled documents available
- 19 July 2010
- Published by Association for Computing Machinery (ACM)
- p. 475-482
Open AccessCombining coregularization and consensus-based self-training for multilingual text categorization
International audienceWe investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the framework of multiview learning, where different languages correspond to different views of the same document, combined with semi-supervised learning in order to benefit from unlabeled documents. We rely on two techniques, coregularization and consensus-based self-training, that combine multiview and semi-supervised learning in different ways. Our approach trains different monolingual classifiers on each of the views, such that the classifiers' decisions over a set of unlabeled examples are in agreement as much as possible, and iteratively labels new examples from another unlabeled training set based on a consensus across language-specific classifiers. We derive a boosting-based training algorithm for this task, and analyze the impact of the number of views on the semi-supervised learning results on a multilingual extension of the Reuters RCV1/RCV2 corpus using five different languages. Our experiments show that coregularization and consensus-based self-training are complementary and that their combination is especially effective in the interesting and very common situation where there are few views (languages) and few labeled documents available
- 29 October 2009
- Published by Springer Nature in Machine Learning
- Vol. 79 (1-2) , 105-121
A co-classification approach to learning from multilingual corpora
- 29 October 2009
- Published by Springer Nature in Machine Learning
- Vol. 79 (1-2) , 105-121
A co-classification approach to learning from multilingual corpora