Learn to build spell checkers and grammar correction models using Python. Explore NLP packages, POS tagging, heuristic methods, and transformer-based spellcheckers for practical use.

Spell Check and Grammar Parsing using Natural Language Processing.png

gector.tar.gz

python3.8

gector job-spa

python 3.7 (no warning)

python3.7

In this course, you’ll learn the details of spell check and grammatical error correction systems by creating them with their basic building blocks. You’ll explore natural language processing packages like NLTK, pandas, spaCy, Fuzz, GECToR, HuggingFace, and more. 

You’ll build the Norvig spellchecker and understand how modern machine learning-based spellcheckers work. This is followed by the mathematical concepts required for identifying part-of-speech (POS) tags for grammatical error checking. You’ll then implement a POS rule-based grammar checker, using a heuristic-based approach to correct grammar mistakes. Finally, you’ll learn to develop a transformer-based spellchecker using HuggingFace’s transformer libraries through a hands-on final project.

After completing this course, you’ll fully understand how modern spellcheckers and grammar correction software work and how these can be integrated into natural language corrector systems such as Grammarly.

Building Grammatical Error Correction Models with Python

- **States**: A set of hidden states that generate the observations. Each state represents a particular condition, category, or context. In NLP, these states might represent parts of speech or syntactic structures.




- **Observations**: A sequence of observations or outputs that are emitted from the hidden states. These observations are what we can observe directly. In NLP, observations could be words in a sentence.




- **Transition probabilities**: A transition matrix that encodes the probabilities of transitioning from one hidden state to another. This matrix captures the dynamics of how the hidden states change over time. Each entry $(i, j)$ in the transition matrix represents the probability of transitioning from state $i$ to state $j$. For example, transitioning from a "Noun" to a "Verb".




- **Emission probabilities**: An emission matrix that specifies the probabilities of emitting particular observations from each hidden state. Each entry $(i, k)$ in the emission matrix represents the probability of emitting observation $k$ from state $i$. For example, the probability the next word is "cat" given the previous word is a "Verb".





Learn what a hidden Markov model is and how it can be represented with transition and emission matrices.

Introduction

Edit Distance

Basic Spellchecker

Modern Spell Check Methods

Part-of-Speech Tagging

Basic Grammatical Error Checking

Modern Grammar Error Correction Methods

Project: Simple Transformer

Conclusion

Auto-Tagging System for Content Categorization

Hidden Markov Models