MGH Research Institute

Ended: Sept. 7, 2018

Special Lecture: AI for Representation and Reasoning in Knowledge Bases of Science
Presented by Andrew McCallum, PhD
Friday September 7 | 1:45-3:30pm | Simches 3.110
Sponsored by the Division of Clinical Research

Agenda
1:45-2:00pm: Introduction
2:00-3:00pm: Lecture- AI for Representation and Reasoning in Knowledge Bases of Science
3:00-3:30pm: Wrap up, Q&A

Andrew McCallum is a Professor and Director of the Information Extraction and Synthesis Laboratory, as well as Director of Center for Data Science in the College of Information and Computer Science at University of Massachusetts Amherst. He has published over 250 papers in many areas of AI, including natural language processing, machine learning and reinforcement learning; his work has received over 50,000 citations. His work on open peer review can be found at http://openreview.net. McCallum's web page is http://www.cs.umass.edu/~mccallum.

Abstract:
Google, Amazon, and Bloomberg have "knowledge graphs" that include celebrities, products and companies. In many ways science could be accelerated if we had a comprehensive knowledge graph of scientific entities---genes, proteins, symptoms, diseases, drugs, chemical compounds, materials, equipment, procedures, problems---and the relations among them. In this talk I will describe advances in machine learning and deep neural networks for extracting entity-relations from the natural language full text of millions scientific papers, as well as for representing and reasoning about the resulting knowledge base. I will introduce "universal schema," our approach that embeds many database schema and natural language expressions into a common semantic vector space. I will also discuss our work in chains of reasoning that employ deep learning to reason about implicit knowledge and scientific "missing links." I will briefly describe our applications of this work to building scientific knowledge bases, including biomedicine (with multiple collaborators), and material science (with Elsa Olivetti at MIT). If there is time and interest, I will also discuss our efforts to revolutionize peer review with our system http://OpenReview.net.

---

Sponsor: MGH Division of Clinical Research