EntityCube and Opinion Organization at MSR TechFest

TechFest is a global gathering of Microsoft researchers from around the world to show off their projects and exchange ideas. The Live Search blog highlights some of the search projects. Some of the highlights include:

EntityCube

EntityCube is an entity search and summarization system that efficiently generates summaries of Web entities from billions of crawled Web pages. The summarized information is used to build an object-level search engine about people, locations, and organizations and explore their relationships.

It is used in Live Product search to extract names, descriptions, images, and prices. It is also used to create structure for the Libra academic search.

Opinion Search
Which collects and organizes review data around products and services. It's currently used to create the "opinion index" in Live product search.

Theory of Information Retrieval Conference CFP

Microsoft Research Cambridge is hosting a conference on theoretical IR (ICTIR) in early September.

Peter Bruza is the invited speaker.

See the important dates.

New IR Blogger: Jeremy Pickens

We've managed to convince one more IR researcher to blog.

Jeremy Pickens, a CIIR alum, started a new blog called Information Retrieval Gupf, see his post What is a Gupf?.

He has already has a few posts to check out:

• Music and Exploratory Search
  
• The 10-speed and the Tricycle
• One Click Away

I've added his blog my feed reader, and blog roll.

Welcome Jeremy!

Yahoo! Research Launches Correlator, a Wikipedia Entity Search Engine

The team at Yahoo! research Barcelona launched Correlator, a prototype Wikipedia search engine. It searches over entities: people, locations, and dates. Instead of search results, it creates a synthetic "summary" page.

Hugo Zaragoza describes it on the What is Correlator page,

The core of Correlator is a search engine capable of returning not only relevant documents, but also relevant sentences and entities. This search engine is the fruit of work at the Yahoo! Research Barcelona lab, where we have been trying to improve search by applying ideas from computational linguistics.

A key differentiating feature is that they extract entities from unstructured text, not just the semi-structured tables like FreeBase.

This comes on the heels of the ESAIR (Exploiting Semantic Annotations in Information Retrieval) 2009 workshop at WSDM.

Thanks to Iadh over the TerrierTeam blog for their coverage.