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

Add to Chrome

Add to Firefox

Picture for Sarath Chandar

Sarath Chandar

MLMLM: Link Prediction with Mean Likelihood Masked Language Model

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

Figure 1 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model

Figure 2 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model

Figure 3 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model

Figure 4 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model

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

Figure 1 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Figure 2 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Figure 3 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Figure 4 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

Access Paper or Ask Questions

Slot Contrastive Networks: A Contrastive Approach for Representing Objects

Jul 18, 2020
Evan Racah, Sarath Chandar

Figure 1 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects

Figure 2 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects

Figure 3 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects

Figure 4 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects

* 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

Figure 1 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Figure 2 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Figure 3 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Figure 4 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

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

Figure 1 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

Figure 2 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

Figure 3 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

Figure 4 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

* 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

Figure 1 for Towards Lossless Encoding of Sentences

Figure 2 for Towards Lossless Encoding of Sentences

Figure 3 for Towards Lossless Encoding of Sentences

Figure 4 for Towards Lossless Encoding of Sentences

* 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

Figure 1 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Figure 2 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Figure 3 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

* 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

Figure 1 for Structure Learning for Neural Module Networks

Figure 2 for Structure Learning for Neural Module Networks

Figure 3 for Structure Learning for Neural Module Networks

Figure 4 for Structure Learning for Neural Module Networks

Access Paper or Ask Questions