Sciweavers

236 search results - page 18 / 48
» Modeling Annotators: A Generative Approach to Learning from ...
Sort
View
CVPR
2010
IEEE
14 years 3 months ago
Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
BMCBI
2004
87views more  BMCBI 2004»
13 years 7 months ago
prot4EST: Translating Expressed Sequence Tags from neglected genomes
Background: The genomes of an increasing number of species are being investigated through generation of expressed sequence tags (ESTs). However, ESTs are prone to sequencing error...
James Wasmuth, Mark L. Blaxter
NAACL
2010
13 years 5 months ago
Good Question! Statistical Ranking for Question Generation
We address the challenge of automatically generating questions from reading materials for educational practice and assessment. Our approach is to overgenerate questions, then rank...
Michael Heilman, Noah A. Smith
INCDM
2010
Springer
146views Data Mining» more  INCDM 2010»
13 years 11 months ago
Learning from Humanoid Cartoon Designs
Abstract. Character design is a key ingredient to the success of any comicbook, graphic novel, or animated feature. Artists typically use shape, size and proportion as the first de...
Md. Tanvirul Islam, Kaiser Md. Nahiduzzaman, Why Y...
KI
2009
Springer
14 years 2 months ago
Presenting Proofs with Adapted Granularity
When mathematicians present proofs they usually adapt their explanations to their didactic goals and to the (assumed) knowledge of their addressees. Modern automated theorem prover...
Marvin Schiller, Christoph Benzmüller