Natural Language Processing

This repository contains all the parallel and distributed assignments for the CSE4022 lab as of Fall'18.

Experiment 1

Import an inaugural speech using nltk.corpus
Display top five frequent words
Create a word cloud (Result)

Experiment 2

Use nltk.corpus to plot a conditional frequency distribution (Result)
Import and use stanford's chinese segmenter (Result)

Experiment 3

Exploring Corpus of Contemporary American english (COCA)

Experiment 4

Remove stopwords from any corpus
Import CMU wordlist
Use wordnet
POS Tag tweets

Experiment 5

Get two texts
Remove stop words
Map the text to vector spaces
Compute cosine(vec1, vec2)
Use SciPy
Take a call if you should do Stemming or not

Experiment 6

Implemented a sequence tagger.
Name Entity Recognition.
Original Link
Credit: guillaumegenthial

Experiment 7

Using CogComp to run NLP tools such as Part-of-Speech tagging, Chunking, Named Entity Recognition, etc.
Original Link
Credit CogComp

Experiment 8

A Chinese word segmenter
Designed using Stanford NLP
A python GUI based application

Digital Assignment 1

Academic review of Apache OpenNLP
Sample code of OpenNLP in R

Authors

Jacob - Initial work - jacob5412