We present a class of web queries whose result is a multi-column relation instead of a collection of unstructured documents as in standard web search. The user specifies the query...
The field of information retrieval has traditionallyfocused on s consistingof titlesand abstracts. As a consequence, many underlying assumptions must be altered for retrieval fro...
Discovering and assembling individual Web services into more complex yet new and more useful Web processes has received significant attention from academia recently. In this thesi...
We propose a method to adapt an existing relation extraction system to extract new relation types with minimum supervision. Our proposed method comprises two stages: learning a lo...
The ADROIT system that we are developing allows automatic discourse analysis of information rich natural language texts extracted directly from the web. We use guidelines and rela...