November 11 , 2010 - Fernando Pereira

Title: Meaning Propagation

Abstract:
Information about the syntax and semantics of terms in context is essential for reliable inference in a variety of document annotation and retrieval tasks. We hypothesize that we can derive most of the relevant information from explicit and implicit relationships between terms in the masses of Web content and user interactions with that content. We have developed graph-based algorithms that efficiently combine many small pieces of textual evidence to bootstrap broad-coverage syntactic and semantic classifiers from small sets of manually-annotated examples.