This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
The integration of facts derived from information extraction systems into existing knowledge bases requires a system to disambiguate entity mentions in the text. This is challengi...
Mark Dredze, Paul McNamee, Delip Rao, Adam Gerber,...
An active learner has a collection of data points, each with a label that is initially hidden but can be obtained at some cost. Without spending too much, it wishes to find a cla...
In this paper we describe our efforts to build a Mandarin Chinese voice search system. We describe our strategies for data collection, language, lexicon and acoustic modeling, as ...
We present a new indexing method named ZINC (for Z-order Indexing with Nested Code) that supports efficient skyline computation for data with both totally and partially ordered at...