Fernando Pereira,

Google

Abstract:

Information about the meanings of terms in context supports useful inferences in a variety of language processing and information retrieval tasks. We hypothesize that much of that information can be derived from explicit and implicit relationships between terms in the masses Web content and user interactions with that content. I will describe initial tests of that hypothesis where we use graph label- propagation methods to combine many small pieces of evidence from unstructured and semi-structured Web text to bootstrap broad-coverage instance-class relationships from a few seed examples.

 

Date: 2010-Jul-19     Time: 15:00:00     Room: Room FA1 – Pavilhão de Informática I (IST)


For more information: