Regina Barzilay received her PhD in Computer Science from Columbia University and spent a year as a postdoc at Cornell University. She is a Delta Electronics professor in the Department of Electrical Engineering and Computer Science and a member at MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Her research interests are in natural language processing, applications of deep learning to chemistry and oncology. Some of Barzilay’s achievements include: the NSF Career Award, the MIT Technology Review TR-35 Award, Microsoft Faculty Fellowship and several Best Paper Awards at NAACL and ACL.
Industry Impact
Machine learning methods are commonly used across engineering and sciences, from computer systems to physics. Likewise, commercial sites such as search engines, recommender system (Netflix, Amazon), advertisers, and financial institutions employ machine learning algorithms for content recommendation, predicting customer behavior, compliance, or risk. Machine learning tries to design and understand computer programs that learn from experience for the purpose of prediction or control.
Recent works
Aspect-Augmented Adversarial Networks for Domain Adaptation
In this project, the proposal is a novel aspect-augmented adversarial network for cross-aspect and cross-domain adaptation tasks. The effectiveness of the approach suggests the potential application of adversarial networks to a broader range of NLP tasks for improved representation learning, such as machine translation and language generation.
Bringing Machine Learning to Cancer Research
Learning to Cure Data collected about millions of cancer patients – their pathology slides, imaging, and other tests – contain answers to many open questions in oncology. This research aims to develop algorithms that can learn from this data to improve models of disease progression, prevent over-treatment, and narrow down to the cure. On the NLP side, the creation of databases which record pertinent cancer features extraction from raw documents. On the computer vision side, the objective is for the deep learning models that focus on personalized assessment from mammogram data focus on early cancer detection.
Chemistry ML
Chemical syntheses are generally designed by practitioners with years of advanced training and experience and carried out in a trial-and-error, labor-intensive manner. The syntheses developed are often unreliable, difficult to scale, and frequently require re-optimization or redevelopment. The aim is to revolutionize chemical synthesis design and development by offering an integrated approach to the synthesis of any organic target molecule.