Scholar
Dzmitry Bahdanau
Google Scholar ID: Nq0dVMcAAAAJ
ServiceNow Research
Citations & Impact
Citations
76,048
H-index
33
i10-index
42
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Invented content-based neural attention, now a core tool in deep-learning-based natural language processing.
- Edge Transformer: a new neural architecture inspired by Prolog and Transformers.
- Systematic Generalization with Edge Transformers (EMNLP 2021)
- LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing (EMNLP 2021)
- PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models (EMNLP 2021)
- DuoRAT: Towards Simpler Text-to-SQL Models (NAACL 2020)
- Towards Ecologically Valid Research on Language User Interfaces
- CLOSURE: Assessing Systematic Generalization of CLEVR Models (ArXiV)
- Systematic Generalization: What Is Required and Can It Be Learned? (ICLR 2019)
- BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop (ICLR 2019)
- Learning to Understand Goal Specifications by Modelling Reward (ICLR 2019)
- An Actor-Critic Algorithm for Sequence Prediction (ICLR 2017)
- End-to-End Attention-based Large Vocabulary Speech Recognition (ICASSP 2016, oral)
- Attention-Based Methods for Speech Recognition (NIPS 2015, spotlight)
- Blocks and Fuel: frameworks for deep learning (2015, technical report)
- Neural Machine Translation by Jointly Learning to Align and Translate
Research Experience
- Research scientist at Element AI (now acquired by ServiceNow), Core Industry Member of Mila, and Adjunct Professor at McGill University.
Education
- PhD at Mila under the supervision of Yoshua Bengio.
Background
- Research interests include Human Language Technologies (HLT), particularly fundamentals of deep learning, foundation model training, task-specific algorithms (especially semantic parsing), and user experience with AI systems. Keywords: semantic parsing, task-oriented dialogue methods, code generation, systematic (compositional) generalization, and sample efficiency of neural models.
Co-authors