Dzmitry Bahdanau
About
Appointed Canada CIFAR AI Chair – 2021
Dzmitry Bahdanau is a Canada CIFAR AI Chair at Mila, an adjunct professor at the School of Computer Science at McGill University, and a research scientist at ServiceNow Research.
Bahdanau’s research goal is to further the adoption and widespread use of language user interfaces for human-computer interaction. His research seeks to align ideas from the disciplines of deep learning, linguistic, and symbolic AI. Topics of key interest to Bahdanau include semantic parsing and task-oriented dialogue models, in particular making such models generalize more systematically, perform effectively with less training data and be easily adaptable to new domains.
Awards
- AI 2000 Most Influential Scholars - Natural Language Processing, 2023
Relevant Publications
Li, Raymond et al. “StarCoder: may the source be with you!” ArXiv abs/2305.06161 (2023): n. pag.
Torsten Scholak, Nathan Schucher, and Dzmitry Bah- danau. (2021). PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Hosseini, A., Reddy, S., Bahdanau, D., Hjelm, R. D., Sordoni, A., & Courville, A. (2021). Understanding by Understanding Not: Modeling Negation in Language Models.
Bergen, L., Bahdanau, D., & O’Donnell, T. J. (2021). Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention.
Scholak, T., Li, R., Bahdanau, D., de Vries, H., & Pal, C. (2020). DuoRAT: Towards Simpler Text-to-SQL Models.
Hui, D. Y. T., Chevalier-Boisvert, M., Bahdanau, D., & Bengio, Y. (2020). BabyAI 1.1.
Żołna, K., Saharia, C., Boussioux, L., Hui, D. Y. T., Chevalier-Boisvert, M., Bahdanau, D., & Bengio, Y. (2020). Combating False Negatives in Adversarial Imitation Learning (Student Abstract). In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 10, pp. 13999-14000).