Natural Language Processing Tutorial in Python

40 ratings
Offered By
Coursera Project Network
2,541 already enrolled
In this Guided Tutorial, you will:

Learn a variety of methods for preprocessing methods for eliminating noise from text data, and lexicon normalization

Implement tokenization methods from scratch in Python code

Utilize open-source libraries such as NLTK to implement techniques such as Part Of Speech tags, Named Entity Recognition, and TF-IDF in Python code

Clock2 hours
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 1-hour long guided tutorial, you will learn basic principles of Natural Language Processing, or NLP. NLP refers to a group of methods for parsing and extracting meaning from human language. In this course, we'll explore the basics of NLP as well as detail the workflow pipeline for NLP and define the three basic approaches to NLP tasks. You'll get the chance to go hands on with a variety of methods for coding NLP tasks ranging from stemming and chunking, Named Entity Recognition, lemmatization, and other tokenization methods. You'll be introduced to open-source libraries such as NLTK, spaCy, Gensim, Pattern, and TextBlob. By the end of this course, you will feel more acquainted with the basics of the NLP workflow and will be ready to begin experimenting and prepare for production-level NLP application coding. I would encourage learners to experiment with the tools and methods discussed in this tutorial. The learner is highly encouraged to experiment beyond the scope of the tutorial. Note: This tutorial works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Language ModelNatural Language ProcessingArtificial Intelligence (AI)Natural Language Toolkit (NLTK)Natural Language Generation

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Become familiar with the NLP workflow

  2. Understand the limitations of specific NLP techniques and how to overcome them by leveraging other techniques

  3. Review a handful of open-source Python libraries that are useful for NLP-related tasks

  4. Tokenize words in a sample text by hand using the Byte Pair Encoding (BPE) method

  5. Utilize multiple noise removal techniques

  6. Utilize several lexicon normalization techniques such as stemming and lemmatization

  7. Make use of object standardization methods, named entity extraction, and Part of Speech Tagging

  8. Learn how to utilize chunking and chinking methods

  9. Utilize methods such as WordNet, Bag of Words, and TF-IDF (Term Frequency — Inverse Document Frequency) to extract meaning from text

How Guided Tutorials work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.