Supervised learning for the legacy document conversion.
Boris ChidlovskiiJérôme FuselierPublished in: ACM Symposium on Document Engineering (2004)
Keyphrases
- supervised learning
- information retrieval
- unsupervised learning
- document images
- document classification
- web documents
- information retrieval systems
- document clustering
- text documents
- retrieval systems
- statistical learning
- reverse engineering
- semi supervised
- active learning
- training set
- supervised machine learning
- multiple instance learning
- document set
- document retrieval
- textual content
- document processing
- document collections
- semi supervised learning
- labeled data
- machine learning
- semantic information
- text categorization
- reinforcement learning
- training data
- neural network
- legacy systems
- database