GitHub - ppouke/NLPProject: Oulu university NLP project

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 28 Commits
__pycache__		__pycache__
.gitignore		.gitignore
header2554.xml		header2554.xml
main.py		main.py
metaphorList.txt		metaphorList.txt
readMetaphorList.py		readMetaphorList.py
readme.txt		readme.txt
testCorpus.txt		testCorpus.txt
wdLoader.py		wdLoader.py

Repository files navigation

Requirements:
- NLTK
   - Stopwords, Reuters
- BNC Corpus ("download" folder) as per project instructions
- WordNet as per project instructions ("wn-domains-3.2" folder)

Running main.py:
- Change variable "usingReut" to determine if Reuters or BNC Corpus is used
- At the bottom of the file, comment and uncomment the parts you do and don't want to run/print

When running first time, stopworded.pkl or stopwordedReut.pkl will be generated. Subsequent runs will utilize these saved files and save processing time.