Task #1857
Extending the remove_header_by_adjective method to improvise the quality of KPs
Start date:
11/03/2021
Due date:
% Done:
0%
Estimated time:
2.00 h
Description
In both C-API & Lib Ref book, there are headers like "other methods", "other functions", "other objects" present which is very specific to the context and neither do they result in quality KPs due to context issues. We need to remove these headers/header variants.
Extend the remove_header_by_adjective method from BR3_IR3_tagger.py to check if:
1) Header is two-word
2) the first word is ADJ and lies within 50 CW (unstemmed) - check both singular and plural forms in the CW
Test this idea with C-API & Lib Ref book.