You are required to implement a python program using NLTK packages to create a framework to pre-process unstructured text.
computer science
Description
1. What is an NLP Library and NLTK??
You are required to implement a python program using NLTK packages to create a framework to pre-process unstructured text. Indicate in your program the steps and processes you have considered. You are also required to give options to user to select the pre-process methods before pre-processing the text.
- Your program should include descriptions of the coding. Marks will be given to a proper
documentation included in the program code. E.g. author's name, program description, date
created, organisation etc.
- Marks also be given to relevant pre-processing methods provided in your
framework. There is no limited number of methods set but all methods provided should be
relevant to pre-processing only. Any irrelevant methods will not be marked.
2. TextBlob, CoreNLP, Gensim, and Pattern. Compare these NLP Python Libraries. Identify
their uses, strength and drawbacks. Give simple example how to use each of these libraries
in a Python program.
- Simple examples must be your own program. It should tested before submitted. DO NOT
copy paste codes from the Web directly.
