Knowledge Driven Semantic Interactions at Web Scale
, Microsoft Research
Date: Thursday, February 20, 2014
Time: 4:00 PM to 5:00 PM Note: all times are in the Eastern Time Zone
Refreshments: 3:45 PM
Location: 32-D463 (Stata Center - Star Conference Room)
Host: Victor Zue and Jim Glass, MIT CSAIL
Contact: Marcia G. Davidson, 617-253-3049, firstname.lastname@example.org
Speaker URL: None
TALK: Knowledge Driven Semantic Interactions at Web Scale
We are witnessing web search industry undergoing dramatic changes at a pace unprecedented since the first search engine went online in 1993. As the world grows more dynamically connected and our life styles become more mobile, modern search engines can no longer just reactively match keywords in queries to keywords in web documents to produce ten blue links. In this talk, we describe a joint effort between Bing and Microsoft Research to fundamentally change the gut and face of a search engine since 2008. The initiative, called Bing Dialog Model, aims at matching users search intents to the knowledge harvested from the web at the semantic level. In addition to reactively answer questions, Bing Dialog Model introduces additional dialog acts, such as confirmation, disambiguation, refinement and digression, that the search engine can execute proactively. We will describe the language understanding and dialog inference aspects of the model in detail and demonstrate them in action.
Kuansan Wang is a Principal Researcher and manager of the Internet Service Research Center (ISRC) at Microsoft Research (MSR), Redmond. He joined MSR Speech Technology Group in 1998, conducting research in the areas of speech recognition, spoken language understanding and multimodal dialog. From 2004 to 2007, he was a software architect at speech product and business incubation groups, helping create and commercialize a wide range of award winning speech products for Microsoft. Since 2007, he has been with MSR ISRC conducting research on web search and machine learning. Dr. Wang is an active member in both academic and industrial communities. He has published more than 50 peered review articles and 140 patents. He is also the author of 6 ISO and 3 W3C standards in the area of speech processing and voice communications.
Created by Marcia G. Davidson at Monday, February 10, 2014 at 11:41 AM.