CL1-Project (Team AAA)

Computational Linguistics Project for Domain Analysis with respect to verbs.

Team Members:

• Akshett Rai Jindal - (2019114001)
• Aashwin Vaish - (2019114014)
• Aravapalli Akhilesh - (2019114016)

Technologies Used

• NLTK : For POS tagging of some of the data - https://www.nltk.org/
• TreeTagger : For POS tagging of the data - https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/

File Structure

• data - contains the given data
• postagged - contains the output of nltk POS tagger and then the manually corrected tags
• AIVerbs.txt - contains all the verbs in the AI Domain
• commonVerbs.py - program to get the common verbs from both the domains
• commonVerbs.txt - the list of common verbs in both the do
• fsm_m1.py - code to tag the module 1 of FMFS
• lightverbsanalysis.txt - analysis of light verbs in the text
• Isverbs.py - progam to tag the words in the files and get the verbs
• postagger.py - gets and tags all the tokens by using nltk
• scraping.py - get the data from a news website
• stgoals.txt - goals of the project
• usageanalysis.txt - analysing some common verbs from both the given domains (Akshett and Aashwin)
• verbanalysis.txt - analysing some common verbs from both the given domains (Akhilesh)
• wrongposanalysis.txt - analysis of the tokens that got tagged wrongly by NLTK