Regina Barzilay

Regina Barzilay is an Israeli-American computer scientist. Barzilay is a School of Engineering Distinguished Professor for AI and Health in the Department of Electrical Engineering and Computer Science and a member of of the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology (MIT). She is an AI faculty lead for Jameel Clinic, an MIT Center for Machine Learning in Health. Barzilay's primary research interest is machine learning models for molecular modeling use cases in drug discovery and clinical AI. She also works in natural language processing (NLP). Barzilay has received a number of awards, including the National Science Foundation (NSF) award, the MIT Technology Review Innovators Under 35 (TR-35) Award, the Microsoft Faculty Fellowship, and the 2020 Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity. In 2017, Barzilay became a recipient of a MacArthur fellowship, an Association of Computational Linguistics (ACL) fellowship, and an Association for the Advancement of Artificial Intelligence (AAAI) fellowship.

Regina Barzilay was born in 1970 in Chisinau, Moldova. At the age of twenty, she immigrated to Israel with her parents. She studied computer science at Ben-Gurion University of Negev, completing her undergraduate degree in 1993 and a Master's in 1998 under advisor Michael Elhadad. In 1998, she moved to New York for a PhD at Columbia University, working with computer science Professor Kathy McKeown. In 2002, she completed her PhD publishing a thesis titled "Information Fusion for Multidocument Summarization: Paraphrasing and Generation."

After completing her PhD, Barzilay spent a year as a postdoc at Cornell University before joining MIT in 2003. Barzilay's research focused on natural language processing and computational linguistics until she was diagnosed with breast cancer in 2014. While undergoing treatment, she was aware of research at MIT that could help her and others. After her diagnosis, she began shifting her research focus to AI in healthcare. In 2016, she started working with the chemical engineering department of the US Defense Advanced Research Projects Agency (DARPA). Barzilay has stated she initially worked on the most effective ways to design molecules without considering the pharmaceutical industry. In May 2016, she was named Delta Delta Electronics Professor of Electrical Engineering and Computer Science at MIT. In 2017, she won a MacArthur Fellowship.

In October 2018, with James Collins and Phil Sharp, Barzilay joined the leadership of a new research project on machine learning in health. Barzilay and Collins were named the faculty co-leads of the Abdul Latif Jameel Clinic for Machine Learning in Health, or J-Clinic. Launched in September 2017, J-clinic is a major collaboration between MIT and Community Jameel. J-Clinic focuses on developing machine learning technologies for the prevention, detection, and treatment of disease. It concentrates on creating and commercializing high-precision, affordable, and scalable machine learning technologies in areas of health care ranging from diagnostics to pharmaceuticals.

In 2020, Barzilay was part of the team that identified a powerful new antibiotic compound, called halicin, using a machine-learning algorithm. Up to the development of halicin, every new antibiotic drug since 1987 was based on already discovered families of molecular structures that have been used extensively. Barzilay's work in healthcare also includes working on an AI system called Mirai that can predict patients at risk of breast cancer within as much as five years. The system scanned thousands of mammograms to uncover subtle patterns that suggest a higher risk of breast cancer.

Barzilay is also a member of the strategic advisory board for Johnson & Johnson (since 2018) and biotech startup Immunai (since 2019). In December 2020, she joined the board of directors of Dewpoint Therapeutics, a biotech research startup based in Boston.

A complete archive of papers authored or coauthored by Barzilay, dating back to 1997, can be found on her website. A list of selected publications is shown below:

• Bao, Yujia, Shiyu Chang, Mo Yu, and Regina Barzilay, “Deriving Machine Attention from Human Rationales,” Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2018.

• Chen, Benson, Regina Barzilay, and Tommi Jaakkola, “Path-Augmented Graph Transformer Network,” ICML Workshop on Learning and Reasoning with Graph-Structured Representations, 2019.
• Yan, Susu, Enrico Santus, Adam Yala, Leonard Wee, Jason Kim, Santiago A. Lozano-Calderon, Joseph H. Schwab, Regina Barzilay, Kevin S. Hughes, and Karen De Amorim Bernstein, “Using Deep Learning Algorithm to Extract Tumour Information from Pathology and Surgical Notes of Chondrosarcoma Patients,” Proceedings of the International Conference on the Use of Computers in Radiation Therapy and the International Conference on Monte Carlo Techniques for Medical Applications (ICCRMCMA), 2019.
• Lehman, Eric, Jay DeYoung, Regina Barzilay and Byron C. Wallace, “Inferring Which Medical Treatments Work from Reports of Clinical Trials,” Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
• Qian, Yujie, Enrico Santus, Zhijing Jin, Jiang Guo, and Regina Barzilay, “GraphIE: A Graph-Based Framework for Information Extraction,” Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
• Schuster, Tal, Ori Ram, Regina Barzilay, and Amir Globerson, “Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-Shot Dependency Parsing,” Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
• Luo, Jiaming, Yuan Cao, and Regina Barzilay, “Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B,” Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
• Jin, Wengong, Kevin Yang, Regina Barzilay, and Tommi Jaakkola, “Learning Multimodal Graph-to-Graph Translation for Molecule Optimization,” Proceedings of International Conference on Learning Representations (ICLR), 2019.
• Ingraham, John, Vikas K. Garg, Regina Barzilay, and Tommi Jaakkola, “Generative Models for Graph-Based Protein Design,” ICLR Workshop on Deep Generative Models for Highly Structured Data, 2019.
• Schuster, Tal, Darsh J. Shah, Yun Jie Serene Yeo, Daniel Filizzola, Enrico Santus, and Regina Barzilay, “Towards Debiasing Fact Verification Models,” Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2019.
• Fisch, Adam, Jiang Guo, and Regina Barzilay, “Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers, “Proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2019.
• Shah, Darsh J., Tal Schuster, and Regina Barzilay, “Automatic Fact Guided Sentence Modification,” Thirty-Fourth Conference of the Association for the Advancement of Artificial Intelligence (AAAI), 2020.
• Tuan, Luu Anh, Darsh J. Shah, and Regina Barzilay, “Capturing Greater Context for Question Generation,” Thirty-Fourth Conference of the Association for the Advancement of Artificial Intelligence (AAAI), 2020.