Question Generation for Generating Textbook Flashcards
One of the most effective ways of retaining the meaning of important concepts in learning materials is to review them in spaced intervals. Millions of students around the world are trying to do exactly that with the help of flash cards. In this short paper, we present a new, transformer-based application for education that automates the process of creating flash cards by automatically generating questions and answers for textbooks. As a proof-of-concept, we report two studies: a) generating questions for textbook summaries written by humans and b) testing a fully-automated pipeline. Several aspects of the quality of the resulting question-answer pairs are evaluated by three annotators. Finally, we describe and make available for review the deployed prototype for the flash card application.
Code (0)
등록된 구현이 없습니다.
Tasks
Question GenerationQuestion-GenerationSimilar Papers 제목 키워드 기반
Unsupervised Generation of Long-form Technical Questions from Textbook Metadata using Structured Templates
We explore the task of generating long-form technical questions from textbooks. Semi-structured metadata of a textbook — the table of contents and the index — provide rich cues for technical question generation. Existing…
FormQuestion GenerationQuestion-GenerationReading ComprehensionI Do Not Understand What I Cannot Define: Automatic Question Generation With Pedagogically-Driven Content Selection
Most learners fail to develop deep text comprehension when reading textbooks passively. Posing questions about what learners have read is a well-established way of fostering their text comprehension. However, many textbo…
Learning TheoryQuestion GenerationQuestion-GenerationReading ComprehensionHow Effective is GPT-4 Turbo in Generating School-Level Questions from Textbooks Based on Bloom's Revised Taxonomy?
We evaluate the effectiveness of GPT-4 Turbo in generating educational questions from NCERT textbooks in zero-shot mode. Our study highlights GPT-4 Turbo's ability to generate questions that require higher-order thinking…
Question GenerationQuestion-GenerationGenerate Logical Equivalence Questions
Academic dishonesty is met with zero tolerance in higher education, yet plagiarism has become increasingly prevalent in the era of online teaching and learning. Automatic Question Generation (AQG) presents a potential so…
Question GenerationExploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applications
In the era of generative artificial intelligence (AI), the fusion of large language models (LLMs) offers unprecedented opportunities for innovation in the field of modern education. We embark on an exploration of prompte…
Multiple-choice