637 search results - page 22 / 128 » Training and documentation |
108
click to vote
INTERSPEECH
2010
14 years 4 months ago
2010
Extractive multi-document summarization is the task of choosing sentences from a set of documents to compose a summary text in response to a user query. We propose a generative ap...
100
click to vote
ICDAR
2009
IEEE
14 years 7 months ago
2009
IEEE
Performance evaluation of document recognition systems is a difficult and practically important problem. Issues arise in defining requirements, in characterizing the system's...
COLING
2002
14 years 9 months ago
2002
This paper proposes a new approach for text categorization, based on a feature projection technique. In our approach, training data are represented as the projections of training ...
LREC
2008
14 years 11 months ago
2008
This paper discusses the problem of utilising multiply annotated data in training biomedical information extraction systems. Two corpora, annotated with entities and relations, an...
DRR
2009
14 years 7 months ago
2009
When is it safe to use synthetic data in supervised classification? Trainable classifier technologies require large representative training sets consisting of samples labeled with...