Browse our site
About
People
Research Areas
Projects
Publications
Seminars
Future
Past
News
You are here:
Home
Seminars
Past
Development of the Bing search engine at the ...
Development of the Bing search engine at the Microsoft Language Development Center
Main information
By:
José Santos
(
CENTRIA
)
Date:
Wednesday, 11th of January 2012, 14h00
Location:
FCT/UNL, Seminar Room (Ed. II)
Abstract
The Microsoft Language Development Center has been collaborating with the Munich Bing Search Technology center to improve the query understanding module of the Bing search engine.
In this talk we will start by providing an overview of the main components of a search engine and then focus our attention on the development of the query understanding module of Bing for Portuguese.
The query understanding module of a search engine is responsible for generating alterations for words in a query so that the altered query may match a broader set of documents and thus increase the likelihood of matching the most relevant documents. For instance, the query 'michael songs' could be rewritten to 'michael jackson musics', which is likely to improve the relevance of the results.
In the talk we will describe the engineering process and do an analysis of the relevance improvements, as measured by NDCG and other objective metrics, on live traffic.
Short-bio
José Santos is currently a post-doctoral fellow at the Microsoft Language Development Center where he has been working on improving Bing’s query rewriting mechanisms.
José holds a Ph.D. degree in Computer Science (2010) from Imperial College London. In the Ph.D., José worked on the theory and implementation of Inductive Logic Programming (ILP) systems, a
first-order logic form of Machine Learning.
José also holds a Licenciatura in Informatics Engineering (2004 FCT-UNL), an MSc in Artificial Intelligence (2006 FCT-UNL) and an MsC in BioInformatics (2007 Imperial College). After graduating in 2004 José did a summer internship at Microsoft Redmond and worked one year as a consultant at Novabase Business Intelligence.
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541
