Improve Academic Query Resolution through BERT-based Question Extraction from Images

TL;DR

This paper introduces a BERT-based deep learning approach to extract questions from images and text, enhancing the accuracy and efficiency of student query resolution in educational technology platforms.

Contribution

It presents a novel BERT-based question extraction method that outperforms rule-based and layout-based approaches for processing student queries in images.

Findings

BERT-based method achieves higher accuracy than rule-based methods.

The approach effectively handles multiple questions and noisy images.

Improves response speed and correctness in Edtech query systems.

Abstract

Providing fast and accurate resolution to the student's query is an essential solution provided by Edtech organizations. This is generally provided with a chat-bot like interface to enable students to ask their doubts easily. One preferred format for student queries is images, as it allows students to capture and post questions without typing complex equations and information. However, this format also presents difficulties, as images may contain multiple questions or textual noise that lowers the accuracy of existing single-query answering solutions. In this paper, we propose a method for extracting questions from text or images using a BERT-based deep learning model and compare it to the other rule-based and layout-based methods. Our method aims to improve the accuracy and efficiency of student query resolution in Edtech organizations.