Bug #1506
Analyse & Discard single-word KPs with "ADV" POS tag
Start date:
08/18/2021
Due date:
% Done:
100%
Estimated time:
2.50 h
Description
In annotated "Python Whirlwind Tour.txt", we have seen some terrible looking tagged keyphrases such as: generally, functionally, etc.
We need to make changes in the BR3_IR3_tagger.py to make sure such KPs are eliminated using their POS tag value. Test your changes with the following datasets:
1. Python Whirlwind Tour.txt
2. Python Tutorial.txt
3. Python 3 - Library Reference.txt
In case elimination of some of the keyphrases is undesirable, find a common word threshold that might help us save them from getting discarded.
For running "Python 3 - Library Reference.txt", you can use master_cands_0.pkl from this link - https://drive.google.com/file/d/1QdZvcVPnPHR4XfKRwscs8PWBJGskRYcF/view?usp=sharing