Question Generation using Natural Language processing

Question Generation using Natural Language processing, available at $22.99, has an average rating of 3.95, with 38 lectures, based on 234 reviews, and has 904 subscribers.

You will learn about Generate assessments like MCQs, True/False questions etc from any content using state-of-the-art natural language processing techniques. Apply recent advancements like BERT, OpenAI GPT-2, and T5 transformers to solve real-world problems in edtech. Use NLP libraries like Spacy, NLTK, AllenNLP, HuggingFace transformers, etc. Deploy transformer models like T5 to production in a Serverless fashion by ONNX quantization and by dockerizing them using FastAPI. Use Google Colab environment to run all these algorithms. This course is ideal for individuals who are Data science students with intermediate skillset in Python and Deep learning. It is particularly useful for Data science students with intermediate skillset in Python and Deep learning.

Enroll now: Question Generation using Natural Language processing

Summary

Title: Question Generation using Natural Language processing

Price: $22.99

Average Rating: 3.95

Number of Lectures: 38

Number of Published Lectures: 38

Number of Curriculum Items: 38

Number of Published Curriculum Objects: 38

Original Price: $22.99

Quality Status: approved

Status: Live

What You Will Learn

Generate assessments like MCQs, True/False questions etc from any content using state-of-the-art natural language processing techniques.

Apply recent advancements like BERT, OpenAI GPT-2, and T5 transformers to solve real-world problems in edtech.

Use NLP libraries like Spacy, NLTK, AllenNLP, HuggingFace transformers, etc.

Deploy transformer models like T5 to production in a Serverless fashion by ONNX quantization and by dockerizing them using FastAPI.

Use Google Colab environment to run all these algorithms.

Who Should Attend

Data science students with intermediate skillset in Python and Deep learning.

Target Audiences

Data science students with intermediate skillset in Python and Deep learning.

This course focuses on using state-of-the-art Natural Language processing techniques to solve the problem of question generation in edtech.

If we pick up any middle school textbook, at the end of every chapter we see assessment questions like MCQs, True/False questions, Fill-in-the-blanks, Match the following, etc.  In this course, we will see how we can take any text content and generate these assessment questions using NLP techniques.

This course will be a very practical use case of NLP where we put basic algorithms like word vectors (word2vec, Glove, etc) to recent advancements like BERT, openAI GPT-2, and T5 transformers to real-world use.

We will use NLP libraries like Spacy, NLTK, AllenNLP, HuggingFace transformers, etc.

All the sections will be accompanied by easy to use Google Colab notebooks. You can run Google Colab notebooks for free on the cloud and also train models using free GPUs provided by Google.

Prerequisites:

This course will focus on the practical use cases of algorithms. A high-level introduction to the algorithms used will be introduced but the focus is not on the mathematics behind the algorithms.

A high-level understanding of deep learning concepts like forward pass, backpropagation, optimizers, loss functions is expected.

Strong Python programming skills with basic knowledge of Natural Language processing and Pytorch is assumed.

The course outline :

? Generate distractors (wrong choices) for MCQ options

Students will use several approaches like Wordnet, ConceptNet, and Sense2vec to generate distractors for MCQ options.

? Generate True or False questions using pre-trained models like sentence BERT, constituency parser, and OpenAI GPT-2

Students will learn to use constituency parser from AllenNLP to split any sentence. They will learn to use GPT-2 to generate sentences with alternate endings and filter them with Sentence BERT.

? Generate MCQs from any content by training a T5 transformer model using the HuggingFace library.

Students will understand the T5 transformer algorithm and use SQUAD dataset to train a question generation model using HuggingFace Transformers library and Pytorch Lightning.

? Generate Fill in the blanks questions

Students will learn to use Python Keyword extraction library to extract keywords, use flashtext library to do fast keyword matching, and visualize fill-in-the-blanks using HTML ElementTree in Colab

? Generate Match the following questions.

Students will learn to use Python Keyword extraction library to extract keywords, use flashtext library to do fast keyword matching, and use BERT to do word sense disambiguation (WSD).

? Deploy question generation models to production.

Deploy transformer models like T5 to production in a serverless fashion by converting them to ONNX format and performing quantization. Create lightweight docker containers using FastAPI for transformer model and deploy on Google Cloud Run.

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction to the Course

Lecture 2: Course Outline

Lecture 3: Code and Dataset Link

Chapter 2: Generate distractors (wrong choices) for MCQ options

Lecture 1: Theory – Generate distractors using wordnet

Lecture 2: Code – Generate Distractors using Wordnet

Lecture 3: Theory – Generate distractors using Conceptnet

Lecture 4: Code – Generate distractors using Conceptnet

Lecture 5: Theory – Generate distractors using Sense2vec

Lecture 6: Code – Generate distractors using Sense2vec

Lecture 7: Theory – Generate distractors using Sentence Transformers

Lecture 8: Code – Generate distractors using Sentence Transformers

Lecture 9: Assignment – Filter the distractors from Sense2vec

Lecture 10: Assignment Solution – Filter the distractors from Sense2vec

Chapter 3: Generate True or False Questions using Constituency Parsing and OpenAI GPT2

Lecture 1: Introduction – Generate True or False Questions

Lecture 2: Theory – Constituency Parsing and OpenAI GPT2

Lecture 3: Code – Split a sentence using constituency parsing

Lecture 4: Code – Another example to split a sentence using constituency parsing

Lecture 5: Code – Generate alternate endings to a split sentence using OpenAI GPT2

Lecture 6: Assignment – Sort the generated sentences in the order of dissimilarity

Lecture 7: Assignment Solution – Sort the generated sentences using Sentence BERT

Chapter 4: Train a question generation model using T5 transformer

Lecture 1: Introduction to T5 – Text to text transfer transformer

Lecture 2: Training methodology, dataset and decoding methods for text generation

Lecture 3: Code – Download SQUAD dataset and preprocess

Lecture 4: Code – Understanding T5 Tokenizer

Lecture 5: Code – Prepare Pytorch Dataset class for T5

Lecture 6: Code – Train T5 transformer model

Lecture 7: Code – Use the trained T5 model to perform inference

Chapter 5: Generate Fill in the blanks questions from any content

Lecture 1: Generate fill in the blanks – Theory

Lecture 2: Generate fill in the blanks – Code

Chapter 6: Generate Match the following questions from any content

Lecture 1: Generate Match the following – Theory

Lecture 2: Extract keywords from any content – Code

Lecture 3: BERT Word Sense Disambiguation (WSD) – Code

Chapter 7: Production deployment of Question Generation Models

Lecture 1: Speed up T5 model by ONNX conversion and use Gradio app for easy visualization

Lecture 2: Install Docker locally in your Operating System

Lecture 3: Dockerize T5 model with FastAPI and create a local API

Lecture 4: Serverless deployment on Google Cloud Run

Chapter 8: Final Project – text2MCQ

Lecture 1: text2MCQ – Theory

Lecture 2: text2MCQ – Code

Instructors

Ramsri Golla
Lead Data Scientist (NLP & CV)

Rating Distribution

1 stars: 3 votes

2 stars: 3 votes

3 stars: 11 votes

4 stars: 79 votes

5 stars: 138 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!