Sarath Chandar
Sarath Chandar
Associate Professor @ Polytechnique Montreal. Mila. Canada CIFAR AI Chair. Canada Research Chair.
Verified email at - Homepage
Cited by
Cited by
A survey of data augmentation approaches for NLP
SY Feng, V Gangal, J Wei, S Chandar, S Vosoughi, T Mitamura, E Hovy
arXiv preprint arXiv:2105.03075, 2021
Guesswhat?! visual object discovery through multi-modal dialogue
H De Vries, F Strub, S Chandar, O Pietquin, H Larochelle, A Courville
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017
The hanabi challenge: A new frontier for ai research
N Bard, JN Foerster, S Chandar, N Burch, M Lanctot, HF Song, E Parisotto, ...
Artificial Intelligence 280, 103216, 2020
An autoencoder approach to learning bilingual word representations
S Chandar, S Lauly, H Larochelle, M Khapra, B Ravindran, VC Raykar, ...
Advances in Neural Information Processing Systems, 1853-1861, 2014
A deep reinforcement learning chatbot
IV Serban, C Sankar, M Germain, S Zhang, Z Lin, S Subramanian, T Kim, ...
arXiv preprint arXiv:1709.02349, 2017
Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus
IV Serban, A García-Durán, C Gulcehre, S Ahn, S Chandar, A Courville, ...
arXiv preprint arXiv:1603.06807, 2016
Complex sequential question answering: Towards learning to converse over linked question answer pairs with a knowledge graph
A Saha, V Pahuja, M Khapra, K Sankaranarayanan, S Chandar
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
Post-hoc interpretability for neural nlp: A survey
A Madsen, S Reddy, S Chandar
ACM Computing Surveys 55 (8), 1-42, 2022
Correlational neural networks
S Chandar, MM Khapra, H Larochelle, B Ravindran
Neural computation 28 (2), 257-285, 2016
Learning to navigate the synthetically accessible chemical space using reinforcement learning
SK Gottipati, B Sattarov, S Niu, Y Pathak, H Wei, S Liu, S Blackburn, ...
International conference on machine learning, 3668-3679, 2020
Do neural dialog systems use the conversation history effectively? an empirical study
C Sankar, S Subramanian, C Pal, S Chandar, Y Bengio
arXiv preprint arXiv:1906.01603, 2019
Dynamic neural turing machine with continuous and discrete addressing schemes
C Gulcehre, S Chandar, K Cho, Y Bengio
Neural computation 30 (4), 857-884, 2018
Toward training recurrent neural networks for lifelong learning
S Sodhani, S Chandar, Y Bengio
Neural computation 32 (1), 1-35, 2020
Hierarchical memory networks
S Chandar, S Ahn, H Larochelle, P Vincent, G Tesauro, Y Bengio
arXiv preprint arXiv:1605.07427, 2016
An empirical investigation of the role of pre-training in lifelong learning
SV Mehta, D Patil, S Chandar, E Strubell
Journal of Machine Learning Research 24 (214), 1-50, 2023
Memory augmented neural networks with wormhole connections
C Gulcehre, S Chandar, Y Bengio
arXiv preprint arXiv:1701.08718, 2017
Towards non-saturating recurrent units for modelling long-term dependencies
S Chandar, C Sankar, E Vorontsov, SE Kahou, Y Bengio
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3280-3287, 2019
Bridge correlational neural networks for multilingual multimodal representation learning
J Rajendran, MM Khapra, S Chandar, B Ravindran
arXiv preprint arXiv:1510.03519, 2015
Patchup: A feature-space block-level regularization technique for convolutional neural networks
M Faramarzi, M Amini, A Badrinaaraayanan, V Verma, S Chandar
Proceedings of the AAAI Conference on Artificial Intelligence 36 (1), 589-597, 2022
Clustering is efficient for approximate maximum inner product search
A Auvolat, S Chandar, P Vincent, H Larochelle, Y Bengio
arXiv preprint arXiv:1507.05910, 2015
The system can't perform the operation now. Try again later.
Articles 1–20