Regina Barzilay

Delta Electronics Professor, EECS.

Faculty Co-Lead, J-Clinic

MacArthur Fellow

MIT Computer Science & Artificial Intelligence Lab
32 Vassar Street, 32-G468
Cambridge, MA 02139
(617) 258-5706
regina@csail.mit.edu
Screen Shot 2020-09-10 at 5.18.41 PM.png

AI Cures Drug Discovery Conference

October 30th, 9am EDT. Virtual Conference.

Announcements

 
Screen Shot 2020-09-10 at 8.41.18 PM.png

Machine learning has been used to automatically translate long-lost languages

Some languages that have never been deciphered could be the next ones to get the machine translation treatment.

Screen Shot 2020-09-10 at 8.41.28 PM.png

Can these researchers catch cancer much earlier than ever before?

From revolutionizing the mammogram to spotting a single tumor cell in the blood...

Screen Shot 2020-09-10 at 8.41.37 PM.png

Looking to Technology to Avoid Doctors’ Offices and Emergency Rooms

Americans are eagerly turning to the latest tech devices in hopes of preventing and detecting medical problems early...

News

 

NLP

Natural Language Processing 

I develop machine learning models that aim to understand and generate natural languages. We are currently witnessing the first generation of NLP tools that have been deployed at scale and are used by millions of people. However, the major component of this success is access to large amounts of training data which machines use to learn mappings between input and output. In many applications and languages, such annotations are not readily available, and are expensive and slow to collect. I am interested in designing algorithms that do not suffer from this annotation dependence. Specifically, we are developing deep learning models that can transfer annotations across domains and languages, that can learn from a few annotated examples by utilizing supplementary data sources, and that can take advantage of human-provided rationales to constrain model structure.

Chemistry

ML Drug Discovery

Today, drug discovery involves practitioners with years of advanced training and is carried out in a trial-and-error, labor-intensive fashion. Our goal is to change a traditional discovery pipeline. In a joint work with chemical engineers and biologists at MIT, we are working on deep learning methods for modeling biological and physicochemical properties, de-novo molecular design, and retrosynthesis.  On the ML side, this area brings many interesting questions related to learning molecular representations, interpretability and robustness. As part of the MLPDS consortium, we are continuously learning  from the deployment of our models in the pharmaceutical industry, directing the development towards our ultimate goal to change the drug discovery process.

Research Interests

 

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Luo, Jiaming, Frederik Hartmann, Enrico Santus, Yuan Cao, and Regina Barzilay

TACL, 2020

A Deep Learning Approach to Antibiotic Discovery

Stokes, Jonathan M., Kevin Yang, Kyle Swanson, Wengong Jin, Andres Cubillos-Ruiz, Nina M. Donghia, Craig R. MacNair, Shawn French, Lindsey A. Carfrae, Zohar Bloom-Ackermann,..., Tommi S. Jaakkola, Regina Barzilay, James J. Collins

Cell, 2020.

Multi-Objective Molecule Generation using Interpretable Substructures

Jin, Wengong, Regina Barzilay, and Tommi Jaakkola

Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.

Papers

 

Group

Teaching

Bio

Awards

  • $1M Association for the Advancement of Artificial Intelligence Squirrel AI Award 2020

  • Top 100 AI Leaders in Drug Discovery & Advanced Healthcare 2019

  • Xconomy Boston Digital Trailblazer 2019

  • Susan Komen Scholar 2018

  • Ruth and Joel Spira Award for Excellence in Teaching 2018

  • AAAI Fellowship 2017

  • ACL Fellowship 2017

  • MacArthur Fellowship 2017

  • Best Paper Award, EMNLP 2016

  • Burgess & Elizabeth Jamieson Award for Excellence in Teaching 2016

  • Delta Electronics Professor 2016

  • Best Paper Honorable Mention, EMNLP 2015

  • Faculty Research Innovation Fellowship 2014

  • Best Student Paper Award, NAACL 2014

  • Best Paper Award, SLT 2010

  • Carolyn Baldwin Morrison Lecture, Cornell 2009

  • Best Paper Award, ACL 2009

  • Ross Career Development Professor 2006

  • Microsoft Faculty Fellowship 2006

  • IEEE Intelligent Systems: “AI Ten to Watch” 2006

  • Technology Review: 35 Top Innovators 2005

  • NSF Career Award 2005

  • Technology Research News: “Top Picks: Technology Research Advances of 2004”

  • Best Paper Award, HLT/NAACL 2004