A weakly-supervised extraction method identifies concepts within conceptual hierarchies, at the appropriate level of specificity (e.g., Bank vs. Institution), to which attribute...
In this paper, we describe our multilingual (or cross-linguistic) information browsing and retrieval system, which is aimed at monolingual users who are interested in information ...
Chinatsu Aone, Nicholas Charocopos, James Gorlinsk...
Traditionally, information extraction from web tables has focused on small, more or less homogeneous corpora, often based on assumptions about the use of <table> tags. A mul...
Information on the Web is not only abundant but also redundant. This redundancy of information has an important consequence on the relation between the recall of an information ga...