Document classification through interactive supervision of document and term labels
DSpace at IIT Bombay
View Archive InfoField | Value | |
Title |
Document classification through interactive supervision of document and term labels
|
|
Creator |
GODBOLE, S
HARPALE, A SARAWAGI, S CHAKRABARTI, S |
|
Description |
Effective incorporation of human expertise, while exerting a low cognitive load, is a critical aspect of real-life text classification applications that is not adequately addressed by batch-supervised high-accuracy learners. Standard text classifiers are supervised in only one way: assigning labels to whole documents. They are thus deprived of the enormous wisdom that humans carry about the significance of words and phrases in context. We present HIClass, an interactive and exploratory labeling package that actively collects user opinion on feature representations and choices, as well as whole-document labels, while minimizing redundancy in the input sought. Preliminary experience suggests that, starting with essentially an unlabeled corpus, very little cognitive labor suffices to set up a labeled collection on which standard classifiers perform well.
|
|
Publisher |
SPRINGER-VERLAG BERLIN
|
|
Date |
2011-10-23T16:00:24Z
2011-12-15T09:11:13Z 2011-10-23T16:00:24Z 2011-12-15T09:11:13Z 2004 |
|
Type |
Article; Proceedings Paper
|
|
Identifier |
KNOWLEDGE DISCOVERY IN DATABASES: PKDD 2004, PROCEEDINGS,3202,185-196
3-540-23108-0 0302-9743 http://dspace.library.iitb.ac.in/xmlui/handle/10054/15170 http://hdl.handle.net/100/1933 |
|
Source |
15th European Conference on Machine Learning/8th European Conference on Principles and Practice of Knowledge Discovery in Databases,Pisa, ITALY,SEP 20-24, 2004
|
|
Language |
English
|
|