The problem statement undertaken is with regard to the children in the age group of 7-14 years, to enhance the learning experience and cultivate a desire of learning, and aid the teachers and the parents. I aim to develop an application that will create an objective questionnaire from a sample text (ex. a lesson or a chapter) to test the knowledge and understanding of the child with respect to the said text using natural language processing and neural networks. To develop an application that prepares a questionnaire based on a text fed into it and grades it. Based on the score obtained, it assigns the pass/fail status.
Nowadays, teachers/professors/tutors spend a lot of time generating test papers and quizzes manually. Similarly, students spend a lot of time on self-analysis. Moreover, students are dependent on their mentors for the self-analysis. Hence, I am working on this NLP project, which has a huge scope of development at this moment. We want to build a computer application system that can help you in calibrating yourself and remove any dependencies on mentors. So this project is relevant to both students and mentors.
- Deep Learning - Developing the neural networks for text summarization, Named Entity Recognition and generating the similar words for incorrect answers.
- Natural Language Processing - Tokenization, Lemmatization, NER
- Language - Python
- AWS - Service for converting the fill in the blank to Questions
- Frameworks and Libraries used
a. Flask - For development of Rest API in order to deploy the deep learning framework.
b. Tensorflow 2.0 - For Deep Learning c. Spacy - Natural Language Processing library d. Gensim - Library for generating similar words as incorrect answers. e. Numpy - Linear Algebra Library for Python f. Pandas - For reading the dataset. g. Word2Vec - Shallow neural network for generating similar words as incorrect options
- Text summarization
- Keyword extraction
- Distractor generator