Invited Speakers

Jason Eisner

Johns Hopkins University/Semantic Machines


TBD

Abstract & Bio

Partha Pratim Talukdar

Google Research/Indian Institute of Science


TBD

Abstract & Bio

Stephan Lewandowsky

University of Bristol


TBD

Abstract & Bio

John Winn

Microsoft Research


Project Alexandria in Viva Topics: AKBC in practice

Abstract & Bio

Raquel Fernández

University of Amsterdam


TBD

Abstract & Bio

Jessica D. Tenenbaum

North Carolina Department of Health and Human Services/Duke University


TBD

Abstract & Bio

He He

New York University


TBD

Abstract & Bio




Speaker abstracts and bios


Dipanjan Das

Google AI

TBD

TBD

Bio

TBD

Back


Jason Eisner

Johns Hopkins University/Semantic Machines

TBD

TBD

Bio

TBD

Back


Douwe Kiela

HuggingFace

TBD

TBD

Bio

TBD

Back


Partha Pratim Talukdar

Google Research/Indian Institute of Science

TBD

TBD

Bio

TBD

Back


TBD

TBD

Bio

TBD

Back


Stephan Lewandowsky

University of Bristol

TBD

TBD

Bio

TBD

Back


John Winn

Microsoft Research

Project Alexandria in Viva Topics: AKBC in practice

At AKBC 2019, we presented Project Alexandria as a solution to inferring a knowledge base completely automatically from unstructured data. Since then, we have built Alexandria into the heart of a new Microsoft product called Viva Topics, launched last year. Viva Topics automatically constructs a knowledge base from an organization’s documents and intranet pages, and surfaces it across a wide range of Microsoft applications including SharePoint, Teams, Outlook and more.

In this talk, I will explore all the challenges the Alexandria team has encountered in transitioning from an academic project to a high quality, scalable production system . These challenges include enabling continual expansion of the knowledge base as new data arrives, allowing people to edit the knowledge base as it is being constructed, bringing together knowledge from a wide variety of structured and unstructured sources, and integrating knowledge across languages. Today, the Alexandria system can discover hundreds of types of entities from tens of millions of documents whilst keeping these entities updated, and integrated with human edits, as the organization evolves. The result is a solution which brings organizational knowledge effortlessly to the fingertips of users across the Microsoft ecosystem.

Bio

John Winn is a senior principal researcher in machine learning from Microsoft Research in Cambridge. In his career, he has worked on large scale automated message passing systems and probabilistic programming, through the development of the Infer.NET framework. He has published on machine learning applications in healthcare, gaming, computational biology and machine vision, and his work has been incorporated into products like the Xbox Kinect and Outlook. In the last decade, he has focused on automatic knowledge base construction using probabilistic programming in the form of Project Alexandria and, more recently, on delivering this work into the new Viva Topics product.

Back


Raquel Fernández

University of Amsterdam

TBD

TBD

Bio

TBD

Back


Jessica D. Tenenbaum

North Carolina Department of Health and Human Services/Duke University

TBD

TBD

Bio

TBD

Back


He He

New York University

TBD

TBD

Bio

TBD

Back