Loading Events

« All Events

  • This event has passed.

[CDS Seminar] Building Knowledge Graph for Products at Scale, Manoj Agarwal, Microsoft India, Thu 2 Dec, 2021 at 5pm

02 Dec @ 5:00 PM -- 6:00 PM

=========== CDS DEPARTMENT SEMINAR ===========
Title: Building A Knowledge Graph for Products at Scale
Speaker: Dr. Manoj Agarwal, Principal Applied Scientist, Microsoft India
Date/Time: Thu 2 Dec, 2021 at 5pm
Venue: Online
==============================================

Abstract

Building a Knowledge Graph is the key to intelligent search in many ways. However, building them is a highly challenging problem. It is an equally or even more challenging problem to build the knowledge graph for products (a product graph). Some of the key challenges are:
1. Product landscape is significantly more complex than general knowledge graphs, as general knowledge graphs typically focus on people, books, movies, or entities belonging to such bigger umbrella categories, whereas there is huge variety in different types of the products.
2. Automatic Product Taxonomy discovery is largely an unmet challenge in the product graph landscape. Accommodating such a huge variety in different products is thus a very challenging problem. Additionally, new types of products keep on emerging.
3. Schema discovery for the given taxonomy is again a significant challenge.
4. Finally, to parse and annotate a product based on discovered taxonomy and schema, to put that information into the form of a knowledge graph <s,p,o> tuple format is very challenging too.
In this talk, we’ll highlight some of these challenges, and showcase our work done to address them. The talk will enrich the general understanding of 1) What is a Knowledge graph? 2) Why is it useful in more intelligent searches? 3) What are the key technical challenges in building it? 4) An approach to handle those in the context of our work done on Product Graph.

Bio

Manoj Agarwal is a Principal Applied Scientist at AI & Research team in Microsoft India, Hyderabad. He received his B. Tech from IIT Roorkee, Masters from University of Texas, Austin and PhD from IIT Bombay. His PhD thesis was awarded ACM India Doctoral Dissertation Award (Honorary Mention).
Before joining Microsoft in 2015, he worked at IBM Research for many years. His research interests are in the areas of web mining, graph mining, pattern recognition, data mining and information retrieval. He has more than 25 patents filed. He has also published close to 25 research papers in reputed journals and conferences such as VLDB, ICDE, WWW, EDBT, DSN, etc., and has won the Best Paper Award twice at prestigious international conferences. He has also received various recognitions from IBM Research and Microsoft AI & Research over the years.

—————————————————————————
Host Faculty: Prof. Yogesh Simmhan

Details

Date:
02 Dec
Time:
5:00 PM -- 6:00 PM

Venue

Online