Natural Language to Structured Knowledge Representations

Speaker Name: 
Siva Reddy
Speaker Title: 
Postdoctoral Researcher
Speaker Organization: 
Department of Computer Science, Stanford University
Start Time: 
Tuesday, February 19, 2019 - 11:00am
End Time: 
Tuesday, February 19, 2019 - 12:15pm
Location: 
E2-599
Organizer: 
Pranav Anand

Abstract:

Computing machinery such as smartphones are ubiquitous, and so will be smart home appliances, self-driving cars and robots in the near future. Enabling these machines with natural language understanding abilities opens up potential opportunities for the broader society to benefit from, e.g., in accessing the world’s knowledge, or in controlling complex machines with little effort. In this talk, we will explore three ways to process language into machine interpretable programs: using external linguistic structures, using structural priors on neural architectures, and using iterative non-linear operations on neural attention distributions.

 

Bio:

Siva Reddy is a postdoctoral researcher in the Computer Science Department at Stanford University, working with Chris Manning. His research goal is to enable machines with natural language understanding abilities to facilitate applications such as question answering and conversational systems. He is currently funded by grants from Amazon, Facebook and SAIL-Toyota. Previously, he was a Google PhD fellow at the University of Edinburgh, working with Mirella Lapata and Mark Steedman. His work experience includes an internship at Google AI and a research position at Sketch Engine.