Language models used in current automatic speech recognition systems are trained on general-purpose corpora and are therefore not relevant to transcribe spoken documents dealing w...
York University participated in the TREC 2008 Blog track, by introducing two opinion finding features. By initially focusing solely on the sentiment terms found in a document, usi...
Modern optical character recognition software relies on human interaction to correct misrecognized characters. Even though the software often reliably identifies low-confidence ...
Michael L. Wick, Michael G. Ross, Erik G. Learned-...
It is crucial in many information systems to organize short text segments, such as keywords in documents and queries from users, into a well-formed topic hierarchy. In this paper,...
One of the key tasks for analyzing conversational data is segmenting it into coherent topic segments. However, most models of topic segmentation ignore the social aspect of conver...
Viet-An Nguyen, Jordan L. Boyd-Graber, Philip Resn...