Talks & Seminars
Title: Context Driven Real Time Summarization of Fast Moving Data Streams and Other Applications of Processing Large Graphs
Mr. Manoj Agarwal, Microsoft India
Date & Time: February 10, 2017 16:00
Venue: Conference Room, C Block, 01st Floor, Department of Computer Science and Engineering, Kanwal Rekhi (KReSIT) Building
From enabling semantic-search to extracting analytical insights from fast-moving data streams in real time, necessity to process large graphs is ubiquitous. However, even though much progress has been made recently in this direction, processing large dynamic graphs is still an open problem. In this talk, we will introduce some recent developments in this area and show one application of processing large dynamic graphs to process fast moving microblog data streams. Microblogging streams typically contain information pertaining to emerging real world events. Due to the rapid pace of messages in these data streams, short message size and many concurrent events, it is often difficult for users to understand the full context behind an arriving message. To address this problem, we propose a novel notion - Contextual Event Summary Threads - and present a technique to extract highly meaningful yet compact event summary threads, capturing the complete context of events appearing in data stream, in real time. Towards that end, we convert this data stream into a large dynamic graph and the track evolution of dense clusters in this graph to track evolution of underlying events in real time. Extensive experiments over real data demonstrate that our technique can summarize live data streams with high accuracy and produce compact event summary threads. We will also try to cover a topic on how graphs can aid in enabling better semantic understanding of text.
Speaker Profile:
Manoj Agarwal is a Senior Applied Scientist at AI & Research team in Microsoft India, Hyderabad. He received his B. Tech from IIT Roorkee (Electronics & Communication), Masters in Electrical & Computer Eng. from University of Texas, Austin (2001), and submitted his PhD thesis, titled "Data as Graph: Search, Discovery, Retrieval", at IIT Bombay (Comp. Sc.) in 2016. Before joining Microsoft in 2015, he worked at IBM Research for close to 14 years. His research interests are in the areas of web mining, graph mining, pattern recognition, data mining and information retrieval. He has 25 patents filed (17 awarded). He has published more than 20 research papers in reputed journals and conferences and has won Best Paper Award twice at prestigious international conferences.
List of Talks


Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback