Feature #1892
In "set_subtract_const_h" method, add penalty for headers with all words within CW 500 unstemmed
Start date:
11/16/2021
Due date:
% Done:
0%
Estimated time:
1.50 h
Description
In the "set_subtract_const_h" method, we assign a penalty to the header based on some condition. We would like to add one more condition to it and check if all the words of the header variants lie in 500 CW unstemmed then it should be penalized. A penalty can be decided after looking at the examples. When you are checking, please use lemmatized forms of the headers.
This is being done to penalize the KPs matching with headers "indexing changes" from "boolean indexing changes"
Let us first try to find all the headers that shall be penalized if we go ahead with it.