Tandem learning: A learning framework for document categorization
Supervised machine learning techniques rely on the availability of ample training data in the form of labeled instances. However, in text, users can have a strong intuition about the relevance of features, that is, words that are indicative of a topic. In this work we show that user prior knowledge...
Main Author: | |
---|---|
Language: | ENG |
Published: |
ScholarWorks@UMass Amherst
2007
|
Subjects: | |
Online Access: | https://scholarworks.umass.edu/dissertations/AAI3275740 |