Departmental Colloquium

Software Engineering at Google: Product Search

Kamal Nigam, Engineering Manager

Google

Friday October 2, 2009
1:00 pm - SENSQ 5317

Hosted by CS Department Industry Board

Abstract

Google's mission is to organize the world's information and make it universally accessible and useful. Google Product Search provides its users with a shopping experience by organizing the world's information about products. This requires understanding products not just as text on a web page but as structured data. This talk will provide an overview of how we apply text mining and machine learning techniques for this challenge and describe in detail a specific wrapper induction technique used to extract product data from web pages.

Biography of Speaker

Kamal Nigam is an engineering manager at Google Pittsburgh, leading projects in product search, information extraction and data mining. He is also adjunct faculty in the machine learning department at Carnegie Mellon University, and serves on the University of Pittsburgh computer science department industry board. His research interests lie at the intersection of text mining, efficient use of human effort, and efficient use of unlabeled data. Prior to joining Google in 2006, he was director of applied research at Intelliseek, a company applying text mining on web data for market research, and previously a research scientist at Whizbang Labs, a company specializing in information extraction on the web. Kamal received his Ph.D. from Carnegie Mellon University in computer science, and his bachelor's degree from Massachusetts Institute of Technology.