Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sarath Chandar

Post-hoc Interpretability for Neural NLP: A Survey

Aug 13, 2021
Andreas Madsen, Siva Reddy, Sarath Chandar

  Access Paper or Ask Questions

Demystifying Neural Language Models' Insensitivity to Word-Order

Jul 29, 2021
Louis Clouatre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar

* 11 pages, 13 figure + appendix 

  Access Paper or Ask Questions

Memory Augmented Optimizers for Deep Learning

Jun 20, 2021
Paul-Aymeric McRae, Prasanna Parthasarathi, Mahmoud Assran, Sarath Chandar

* 24 Pages. Currently under review 

  Access Paper or Ask Questions

Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?

Jun 20, 2021
Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar

* Accepted at SIGDial 2021. arXiv admin note: substantial text overlap with arXiv:2008.10427 

  Access Paper or Ask Questions

A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss

Jun 20, 2021
Prasanna Parthasarathi, Mohamed Abdelsalam, Joelle Pineau, Sarath Chandar

* Accepted at SIGDial 2021 

  Access Paper or Ask Questions

A Survey of Data Augmentation Approaches for NLP

May 29, 2021
Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy

* Accepted to ACL 2021 Findings. GitHub repo with paper list at 

  Access Paper or Ask Questions

TAG: Task-based Accumulated Gradients for Lifelong learning

May 11, 2021
Pranshu Malviya, Balaraman Ravindran, Sarath Chandar

  Access Paper or Ask Questions

Continuous Coordination As a Realistic Scenario for Lifelong Learning

Mar 04, 2021
Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville, Sarath Chandar

  Access Paper or Ask Questions

IIRC: Incremental Implicitly-Refined Classification

Jan 11, 2021
Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar

  Access Paper or Ask Questions

Maximum Reward Formulation In Reinforcement Learning

Oct 08, 2020
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar

* 13 pages, 5 figures 

  Access Paper or Ask Questions

MLMLM: Link Prediction with Mean Likelihood Masked Language Model

Sep 15, 2020
Louis Clouatre, Philippe Trempe, Amal Zouaq, Sarath Chandar

  Access Paper or Ask Questions

How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Aug 24, 2020
Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar

  Access Paper or Ask Questions

Slot Contrastive Networks: A Contrastive Approach for Representing Objects

Jul 18, 2020
Evan Racah, Sarath Chandar

* Presented at ICML 2020 Workshop: Object-Oriented Learning (OOL): Perception, Representation, and Reasoning 

  Access Paper or Ask Questions

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Jul 07, 2020
Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar

  Access Paper or Ask Questions

PatchUp: A Regularization Technique for Convolutional Neural Networks

Jun 14, 2020
Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan, Vikas Verma, Sarath Chandar

  Access Paper or Ask Questions

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

May 20, 2020
Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam M. J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio

* added the statistics of top-100 compounds used logP metric with scaled components added values of the initial reactants to the box plots some values in tables are recalculated due to the inconsistent environments on different machines. corresponding benchmarks were rerun with the requirements on github. no significant changes in the results. corrected figures in the Appendix 

  Access Paper or Ask Questions

Towards Lossless Encoding of Sentences

Jun 04, 2019
Gabriele Prato, Mathieu Duchesneau, Sarath Chandar, Alain Tapp

* Accepted at ACL 2019 

  Access Paper or Ask Questions

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Jun 04, 2019
Chinnadhurai Sankar, Sandeep Subramanian, Christopher Pal, Sarath Chandar, Yoshua Bengio

* To appear at ACL 2019 

  Access Paper or Ask Questions

Structure Learning for Neural Module Networks

May 27, 2019
Vardaan Pahuja, Jie Fu, Sarath Chandar, Christopher J. Pal

  Access Paper or Ask Questions

The Hanabi Challenge: A New Frontier for AI Research

Feb 01, 2019
Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, Michael Bowling

* 37 pages, 5 figures, submitted to Artificial Intelligence 

  Access Paper or Ask Questions

Environments for Lifelong Reinforcement Learning

Dec 06, 2018
Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup

* Accepted at 2nd Continual Learning Workshop, Neural Information Processing Systems (NeurIPS) 2018 

  Access Paper or Ask Questions

On Training Recurrent Neural Networks for Lifelong Learning

Nov 16, 2018
Shagun Sodhani, Sarath Chandar, Yoshua Bengio

* Accepted at the Continual Learning Workshop , NIPS 2018 

  Access Paper or Ask Questions

Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph

Oct 04, 2018
Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar

* Accepted in AAAI'18 

  Access Paper or Ask Questions

Language Expansion In Text-Based Games

May 17, 2018
Ghulam Ahmed Ansari, Sagar J P, Sarath Chandar, Balaraman Ravindran

* 9 pages. arXiv admin note: text overlap with arXiv:1511.06295 by other authors 

  Access Paper or Ask Questions

A Deep Reinforcement Learning Chatbot (Short Version)

Jan 20, 2018
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio

* 9 pages, 1 figure, 2 tables; presented at NIPS 2017, Conversational AI: "Today's Practice and Tomorrow's Potential" Workshop 

  Access Paper or Ask Questions