Problem Specification

1
Problem Specification
Paper Combining Classifiers to Identify Online
Databases Where are the online databases
in web ? Which forms are doors to these
databases ? Which are relevant to my domain ?

2
Solution

• HIFI Hierarchical Form Identifier

FFC
GFC
DSFC
GFC Searchable Vs Non-searchable Decision Tree
Selection lists/Text Boxes Domain independent
DSFC Relevant Vs Irrelevant SVM Form Tag bag
model Domain Specific
3
Critique

• How far ?
• Structure of web page evolving.
• Interface of online databases changing web
  services etc.

4
Relation to CSE 494
DSFC
Text classification
Information Integration
HIFI
cse494
Information Extraction
GFC
5
Problem Specification
Solution

• HIFI Hierarchical Form Identifier

• Paper
• Combining Classifiers to Identify
• Online Databases
• Where are the online databases in web ?
• Which forms are doors to databases ?
• Which are relevant to my domain ?

FFC
GFC
DSFC

• GFC
• Searchable Vs Non-searchable
• Decision Tree
• HTML Tags
• Domain independent

• DSFC
• Relevant Vs Irrelevant
• SVM
• Form Tag bag model
• Domain Specific

Relation to CSE 494
Critical View
DSFC
Text classification

• Structure of web page evolving.
• Interface of online databases changing
• web services etc.

Information Integration
cse494
HIFI
Information Extraction
GFC