Encoder-Decoder with Attention Mechanisms for Developing Question Generation Models in Education
Year: 2020
Type: article
Abstract: This research aims to create a system that generates questions that are used in higher education circles.This study uses a machine learning approach is to create questions that refer to the taxonomic bloom.This study also uses encoder-decoder and attention techniques that are used to look for context.The dataset used consisted of 93,000 pairs of questions.Data were trained repeatedly with a percentage of dataset 80:20 and classified using six levels in bloom's taxonomy and based on vector embedding.The results of this study prove that the encoder-decoder model with attention produces better and easier questions than other models.Evaluation of the question-producing system by comparing the two activation functions, namely hyperbolic tangential and sigmoid, shows that the sigmoid function can reduce the value of the loss function to 0.001, which means it can minimize the error factor.
Author: Bambang Dwi Wijanarko
Institution: Binus University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: bronze
OpenAlex ID: W3085621573