D
Dzmitry Bahdanau
Researcher at McGill University
Publications - 61
Citations - 72393
Dzmitry Bahdanau is an academic researcher from McGill University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 26, co-authored 53 publications receiving 58851 citations. Previous affiliations of Dzmitry Bahdanau include Université de Montréal & Jacobs University Bremen.
Papers
More filters
CLOSURE: Assessing Systematic Generalization of CLEVR Models.
Dzmitry Bahdanau,Harm de Vries,Timothy J. O'Donnell,Shikhar Murty,Philippe Beaudoin,Yoshua Bengio,Aaron Courville +6 more
TL;DR: Surprisingly, it is found that an explicitly compositional Neural Module Network model also generalizes badly on CLOSURE, even when it has access to the ground-truth programs at test time.
Proceedings ArticleDOI
Commonsense mining as knowledge base completion? A study on the impact of novelty
Stanisław Jastrzębski,Dzmitry Bahdanau,Seyedarian Hosseini,Michael Noukhovitch,Yoshua Bengio,Jackie Chi Kit Cheung +5 more
TL;DR: This paper proposed novelty of predicted triples with respect to the training set as an important factor in interpreting results, and critically analyzed the difficulty of mining novel commonsense knowledge, and showed that a simple baseline method that outperforms the previous state of the art on predicting more novel triples.
Journal ArticleDOI
SantaCoder: don't reach for the stars!
Loubna Ben Allal,Raymond T. Li,Denis Kocetkov,Chenghao Mou,Christopher Akiki,Carlos Muñoz Ferrandis,Niklas Muennighoff,Mayank Mishra,Alexander Gu,Manan Dey,Logesh Kumar Umapathi,Carolyn J. Anderson,Yangtian Zi,Joel Poirier,Hailey Schoelkopf,Sergey Troshin,Dmitry Abulkhanov,Manuel Romero,Michael F. Lappert,Francesco De Toni,Bernardo Garc'ia del R'io,Qian Liu,Shamik Bose,Urvashi Bhattacharyya,Terry Yue Zhuo,I. Yu,Paulo Villegas,M. Zocca,Sourab Mangrulkar,David Lansky,Huu Nguyen,Danish Contractor,Luisa Lina Villa,Jia Li,Dzmitry Bahdanau,Yacine Jernite,Sean Hughes,D. S. Fried,Arjun Guha,Harm de Vries,Leandro von Werra +40 more
TL;DR: InCoder-6.7B and CodeGen-Multi-2.1B as discussed by the authors train 1.1b parameter models on the Java, JavaScript, and Python subsets of The Stack and evaluate them on the MultiPL-E text-to-code benchmark.
Posted Content
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
Jean Pouget-Abadie,Dzmitry Bahdanau,Bart van Merriënboer,Kyunghyun Cho,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +6 more
TL;DR: The authors propose to segment an input sentence into phrases that can be easily translated by the NMT model and concatenate the translated clauses to form a final translation, which shows a significant improvement in translation quality for long sentences.
Posted Content
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Maxime Chevalier-Boisvert,Dzmitry Bahdanau,Salem Lahlou,Lucas Willems,Chitwan Saharia,Thien Huu Nguyen,Yoshua Bengio +6 more
TL;DR: The BabyAI research platform is introduced to support investigations towards including humans in the loop for grounded language learning and puts forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.