Sciweavers

38 search results - page 6 / 8
» Using word sense discrimination on historic document collect...
Sort
View
EACL
2006
ACL Anthology
14 years 10 months ago
A Figure of Merit for the Evaluation of Web-Corpus Randomness
In this paper, we present an automated, quantitative, knowledge-poor method to evaluate the randomness of a collection of documents (corpus), with respect to a number of biased pa...
Massimiliano Ciaramita, Marco Baroni
DAS
2006
Springer
15 years 1 months ago
Aligning Transcripts to Automatically Segmented Handwritten Manuscripts
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...
Jamie L. Rothfeder, R. Manmatha, Toni M. Rath
DL
1994
Springer
191views Digital Library» more  DL 1994»
15 years 1 months ago
Corpus Linguistics for Establishing The Natural Language Content of Digital Library Documents
Digital Libraries will hold huge amounts of text and other forms of information. For the collections to be maximally useful, they must be highly organized with useful indexes and ...
Robert P. Futrelle, Xiaolan Zhang 0002, Yumiko Sek...
CHI
2003
ACM
15 years 2 months ago
Breakingstory: visualizing change in online news
BreakingStory is an interactive system for visualizing change in online news. The system regularly collects the text from the front pages of international daily news web sites. It...
Jean Anne Fitzpatrick, James Reffell, Moryma Aydel...
PAMI
2007
101views more  PAMI 2007»
14 years 9 months ago
A Thousand Words in a Scene
— This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our wo...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...