Siva Reddy
About
Appointed Canada CIFAR AI Chair – 2020
Renewed Canada CIFAR AI Chair – 2025
Siva Reddy is a Canada CIFAR AI Chair at Mila and an assistant professor in the School of Computer Science and the Department of Linguistics at McGill University.
Reddy’s area of research is natural language processing. His research goal is to enable machines with language understanding abilities such that conversing with machines feels as natural as conversing with humans. Along this process, he hopes to discover fundamental representations of language, both symbolic and distributional, that allow us to study the connection between language and meaning.
Reddy’s expertise includes building symbolic and deep learning models for language understanding. Additionally, he works on problems such as semantic parsing, question answering, reading comprehension, and conversational systems.
Awards
- Amazon Research Award (Co-Investigator, 2018)
- Google PhD Fellowship, 2015
- Best Paper Award, International Joint Conference on Natural Language Processing, 2011
Relevant Publications
Ponti, E. M., Aralikatte, R., Shrivastava, D., Reddy, S., & Søgaard, A. (2021). Minimax and Neyman-Pearson Meta-Learning for Outlier Languages.
Sachan, D. S., Reddy, S., Hamilton, W., Dyer, C., & Yogatama, D. (2021). End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering.
Shen, Y., Tan, S., Sordoni, A., Reddy, S., & Courville, A. (2021, June). Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 1660-1672).
Hosseini, A., Reddy, S., Bahdanau, D., Hjelm, R. D., Sordoni, A., & Courville, A. (2021). Understanding by Understanding Not: Modeling Negation in Language Models.
Nadeem, M., Bethke, A., & Reddy, S. (2020). Stereoset: Measuring stereotypical bias in pretrained language models.