Created by Cécile MACAIRE & Ludivine ROBERT
Python script which extracts and annotates terms from a corpus of articles about "Text-to-Speech System".
The goal of this project is to develop a term identification system for a specific domain. It has been realized under the Terminology course, as part of the Natural language processing masters' degree in Université de Lorraine (Nancy).
Pandas
Spacy
The script to run is termsprocessing.py. The following instructions need to be filled out:
- type of annotation:
- 1 = terms annotation
- 2 = terms annotation and IOB tags
- 3 = terms annotation, IOB tags and Part-Of-Speech (POS) tags
- input file that you want to annotate in .txt format
- name of your output file (also in .txt format)
Finally, enter the following command in your terminal:
python termsprocessing.py -n 1 -i input.txt -o output.txt