Bug #1507
Bad looking key phrases following the pattern: "word1, word2" while the header variant is "word1 word2"
Status:
Closed
Priority:
Normal
Assignee:
-
Target version:
-
Start date:
08/18/2021
Due date:
% Done:
0%
Estimated time:
2.50 h
Description
In Python Whirlwind Tour.txt, we are seeing some tagged KPs such as "python, code" linked to the "How to run Python Code" document. It is certainly undesirable. Some of such instances were observed in Python 3 - Library Reference.txt as well.
Make changes in BR3_IR3_tagger.py to make sure such KPs are eliminated. Test the changes with the following datasets:
1. Python Whirlwind Tour.txt
2. Python Tutorial.txt
3. Python 3 - Library Reference.txt
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
Files
| Screenshot from 2021-08-18 20-27-27.png (68.4 KB) Screenshot from 2021-08-18 20-27-27.png | Screenshot for reference |
