This paper presents a method of automatically creating hypermedia documents from conventional transcriptions of television programs. Using parallel text alignment techniques, the ...
Given a strong match between regions of two sequences, how far can the match be meaningfully extended if gaps are allowed in the resulting alignment? The aim is to avoid searching...
Today's digital libraries increasingly include not only printed text but also scanned handwritten pages and other multimedia material. There are, however, few tools available...
Abstract. Training and evaluation of techniques for handwriting recognition and retrieval is a challenge given that it is difficult to create large ground-truthed datasets. This is...
This paper proposes a semi-supervised boosting approach to improve statistical word alignment with limited labeled data and large amounts of unlabeled data. The proposed approach ...