Automated Extraction of Answer Candidates for Question Generation

A hybrid embedding approach for short-answer grading using BERT and universal sentence encoder

Evaluating learner responses is vital in assessment, especially for free-text answers, which are most challenging due to their demand for reasoning and expression. These responses reflect the learner’s understanding of the subject matter. However, manual evaluation is time-consuming and also prone to human error, highl...

A Context-Aware Subjective Question Generation Model Using a Domain-Specific Fine-Tuned T5 Transformer

Mock tests play an important role in preparing for academic and competitive examinations, and most mock tests have been designed based on the Question Answering (QA) technique, which is one of the areas in Natural Language Processing (NLP). There are two main tasks in QA: Automatic Question Generation (AQG), which enta...

Text Based Question Answering System

The “Question Answering System Based on Paragraph” is a Python-based web application designed to provide users with a seamless experience in extracting answers from textual content. Built with Flask, the application allows users to securely log in, paste a paragraph of text into an input field, and ask questions about...

From Generation to Evaluation: A Resource for Error-Categorized Question Generation from Video Transcripts

Design and Implementation of a Sentence-BERT-Driven Semantic Matching Model for Automated Evaluation of Theory Answers

EvalAI grades theory answers on meaning rather than wording, using Sentence-BERT to measure how semantically similar a student's response is to a lecturer-provided reference answer, showing that semantic grading of this quality can be delivered within a deployable web application without specialised machine learning in...

Portable Document Format Text Analysis for Automated Question Answering

An automated question answering system for PDF text analysis using Natural Language Processing (NLP) and transformer-based models that is capable of generating relevant and contextually accurate responses from PDF-based textual data is presented.