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

Add to Chrome

Add to Firefox

Picture for Dzmitry Bahdanau

Dzmitry Bahdanau

DuoRAT: Towards Simpler Text-to-SQL Models

Oct 21, 2020
Torsten Scholak, Raymond Li, Dzmitry Bahdanau, Harm de Vries, Chris Pal

Figure 1 for DuoRAT: Towards Simpler Text-to-SQL Models

Figure 2 for DuoRAT: Towards Simpler Text-to-SQL Models

Figure 3 for DuoRAT: Towards Simpler Text-to-SQL Models

Figure 4 for DuoRAT: Towards Simpler Text-to-SQL Models

* Code is available at https://github.com/ElementAI/duorat

Access Paper or Ask Questions

Towards Ecologically Valid Research on Language User Interfaces

Jul 28, 2020
Harm de Vries, Dzmitry Bahdanau, Christopher Manning

Figure 1 for Towards Ecologically Valid Research on Language User Interfaces

Figure 2 for Towards Ecologically Valid Research on Language User Interfaces

Figure 3 for Towards Ecologically Valid Research on Language User Interfaces

Figure 4 for Towards Ecologically Valid Research on Language User Interfaces

Access Paper or Ask Questions

BabyAI 1.1

Jul 24, 2020
David Yu-Tung Hui, Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Yoshua Bengio

Figure 1 for BabyAI 1.1

Figure 2 for BabyAI 1.1

Figure 3 for BabyAI 1.1

Figure 4 for BabyAI 1.1

* 9 pages, 1 figure, technical report

Access Paper or Ask Questions

Combating False Negatives in Adversarial Imitation Learning

Feb 02, 2020
Konrad Zolna, Chitwan Saharia, Leonard Boussioux, David Yu-Tung Hui, Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Yoshua Bengio

Figure 1 for Combating False Negatives in Adversarial Imitation Learning

Figure 2 for Combating False Negatives in Adversarial Imitation Learning

Figure 3 for Combating False Negatives in Adversarial Imitation Learning

Figure 4 for Combating False Negatives in Adversarial Imitation Learning

* This is an extended version of the student abstract published at 34th AAAI Conference on Artificial Intelligence

Access Paper or Ask Questions

Automated curriculum generation for Policy Gradients from Demonstrations

Dec 01, 2019
Anirudh Srinivasan, Dzmitry Bahdanau, Maxime Chevalier-Boisvert, Yoshua Bengio

Figure 1 for Automated curriculum generation for Policy Gradients from Demonstrations

Figure 2 for Automated curriculum generation for Policy Gradients from Demonstrations

Figure 3 for Automated curriculum generation for Policy Gradients from Demonstrations

Figure 4 for Automated curriculum generation for Policy Gradients from Demonstrations

* Accepted to Deep RL Workshop at NeurIPS 2019

Access Paper or Ask Questions

Systematic Generalization: What Is Required and Can It Be Learned?

Nov 30, 2018
Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch, Thien Huu Nguyen, Harm de Vries, Aaron Courville

Figure 1 for Systematic Generalization: What Is Required and Can It Be Learned?

Figure 2 for Systematic Generalization: What Is Required and Can It Be Learned?

Figure 3 for Systematic Generalization: What Is Required and Can It Be Learned?

Figure 4 for Systematic Generalization: What Is Required and Can It Be Learned?

* Preprint. Work in progress

Access Paper or Ask Questions

BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

Oct 27, 2018
Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, Yoshua Bengio

Figure 1 for BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

Figure 2 for BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

Figure 3 for BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

Figure 4 for BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop

* Preprint. Work in progress

Access Paper or Ask Questions

Learning to Understand Goal Specifications by Modelling Reward

Oct 02, 2018
Dzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Pushmeet Kohli, Edward Grefenstette

Figure 1 for Learning to Understand Goal Specifications by Modelling Reward

Figure 2 for Learning to Understand Goal Specifications by Modelling Reward

Figure 3 for Learning to Understand Goal Specifications by Modelling Reward

Figure 4 for Learning to Understand Goal Specifications by Modelling Reward

* 18 pages, 8 figures

Access Paper or Ask Questions

Commonsense mining as knowledge base completion? A study on the impact of novelty

Apr 24, 2018
Stanisław Jastrzębski, Dzmitry Bahdanau, Seyedarian Hosseini, Michael Noukhovitch, Yoshua Bengio, Jackie Chi Kit Cheung

Figure 1 for Commonsense mining as knowledge base completion? A study on the impact of novelty

Figure 2 for Commonsense mining as knowledge base completion? A study on the impact of novelty

Figure 3 for Commonsense mining as knowledge base completion? A study on the impact of novelty

Figure 4 for Commonsense mining as knowledge base completion? A study on the impact of novelty

* Published in Workshop on New Forms of Generalization in Deep Learning and Natural Language Processing (NAACL 2018)

Access Paper or Ask Questions