Sciweavers

2206 search results - page 373 / 442
» Using Classification to Generate Text
Sort
View
AND
2009
14 years 9 months ago
Edge noise in document images
A degradation model that describes many image degradations produced by desktop scanning is used to study the edge noise that is present in bilevel document images. The standard de...
Craig McGillivary, Chris Hale, Elisa H. Barney Smi...
KCAP
2011
ACM
14 years 2 months ago
Language resources extracted from Wikipedia
Wikipedia provides an interesting amount of text for more than hundred languages. This also includes languages where no reference corpora or other linguistic resources are easily ...
Denny Vrandecic, Philipp Sorg, Rudi Studer
ACL
2012
13 years 1 months ago
Reducing Wrong Labels in Distant Supervision for Relation Extraction
In relation extraction, distant supervision seeks to extract relations between entities from text by using a knowledge base, such as Freebase, as a source of supervision. When a s...
Shingo Takamatsu, Issei Sato, Hiroshi Nakagawa
CVPR
2005
IEEE
16 years 1 months ago
Evaluating Image Retrieval
We present a comprehensive strategy for evaluating image retrieval algorithms. Because automated image retrieval is only meaningful in its service to people, performance character...
Nikhil V. Shirahatti, Kobus Barnard
ICPR
2004
IEEE
16 years 17 days ago
Decoder Banks: Versatility, Automation, and High Accuracy without Supervised Training
A methodology using decoder banks is proposed for high-accuracy, fully automatic recognition of machine printed text across a wide range of challenging image qualities, without re...
Henry S. Baird, Prateek Sarkar