Welcome to the Natural Language Processing (NLP) Experiments repository! This repository contains a collection of projects and resources designed to help you explore and understand various NLP techniques and concepts using Python.
- Basic Corpus Analysis
- Bigram Table
- Constituency Parsing
- Naive Bayes Text Classification
- Named Entity Recognition
- POS Tags Using Viterbi
- POS Using Hidden Markov Model
- Project on Translator
- Stemmer vs Lemmatizer
This project involves basic analysis of a text corpus, including frequency distribution, word cloud generation, and more.
- Folder:
Basic_Corpus_Analysis
- Contents: Scripts and notebooks for analyzing text corpora
Generate and analyze bigram tables to understand word pair frequencies within a corpus.
- Folder:
Bigram_Table
- Contents: Scripts and notebooks for creating and analyzing bigram tables
Explore constituency parsing techniques to understand the syntactic structure of sentences.
- Folder:
Constituency_Parsing
- Contents: Scripts and examples for performing constituency parsing
Implement Naive Bayes algorithms for text classification tasks, including sentiment analysis and spam detection.
- Folder:
Naive_Bayes_Text_Classification
- Contents: Notebooks and scripts for Naive Bayes text classification
Identify and classify named entities in text using various NLP techniques.
- Folder:
Named_Entity_Recognition
- Contents: Scripts and notebooks for performing named entity recognition
Implement the Viterbi algorithm to assign part-of-speech (POS) tags to words in a sentence.
- Folder:
POS_Tags_Using_Viterbi
- Contents: Scripts and examples using the Viterbi algorithm for POS tagging
POS Using Hidden Markov Model
Use Hidden Markov Models (HMMs) to perform part-of-speech tagging on text data.
- Folder:
POS_Using_Hidden_Markov_Model
- Contents: Notebooks and scripts for POS tagging using HMMs
Develop a translator project to convert text from one language to another using NLP techniques.
- Folder:
Project
- Contents: Scripts, notebooks, and resources for building a language translator
Compare stemming and lemmatization techniques to preprocess text data effectively.
- Folder:
Stemmer_vs_Lemmatizer
- Contents: Scripts and notebooks comparing stemmers and lemmatizers
This repository is licensed under the MIT License. See the LICENSE file for more details.
If you have any questions or feedback, please reach out to us at desicoder14@gmail.com.
Happy Experimenting!