Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Automated question generation and question answering from Turkish texts
Download
index.pdf
Date
2022-1-01
Author
Akyön, Fatih Çağatay
Çavuşoğlu, Devrim
Cengiz, Cemil
Altinuç, Sinan Onur
Temizel, Alptekin
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
146
views
73
downloads
Cite This
All rights reserved.While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multitask setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work that performs automated text-to-text question generation from Turkish texts. Experimental evaluations show that the proposed multitask setting achieves state-of-the-art Turkish question answering and question generation performance on TQuADv1, TQuADv2 datasets and XQuAD Turkish split. The source code and the pretrained models are available at https://github.com/obss/turkish-question-generation.
Subject Keywords
answer extraction
,
multitask
,
question answering
,
question generation
,
transformer
,
Turkish
URI
https://hdl.handle.net/11511/101785
Journal
Turkish Journal of Electrical Engineering and Computer Sciences
DOI
https://doi.org/10.55730/1300-0632.3914
Collections
Graduate School of Informatics, Article
Suggestions
OpenMETU
Core
DESIGN, DEVELOPMENT AND IMPLEMENTATION OF A QUESTION-ANSWER BASED INSTRUCTIONAL DESIGN THEORY
Ataş, Amine Hatun; Yıldırım, Zahide (2017-11-18)
The purpose of this study is to document design, development, and implementation of a question-answer based instructional design theory. Sigel and Saunders (1977) state that many studies report the benefits of asking questions and being asked questions as enhancing students' thinking and reflects students' thinking process. The impact of asking question or being asked questions are inevitably influential on learning. As students experience quality questions and questioning, their awareness of learning arise...
Design, Development and Evaluation of Educational Software
Çağıltay, Kürşat(2009)
This course is designed to provide the necessary skills and background in formulating and using criteria and procedures for development and evaluation of instructional materials; synthesis of research; resources in the field. The course also underlines major steps and techniques used in design development and evaluation of instructional software.
Online Instructional Personal Environment for Deep Language Learning
Tochon, Francois V.; Karaman, Abdullah Cendel; Ökten, Celile Eren (2014-01-01)
This article focuses on the creation of instructional materials that serve as a personal environment for learning a less-commonly-taught language. The study aims to raise awareness of ways in which digital personal learning environments can be used in tandem with more formal learning strategies. The study explores self-regulated language learning within personal environments created for intermediate and advanced Turkish. We reviewed the conceptual background for the approach as well as the project-based lea...
Exploration of instructional design process and experience of novice instructional designers through the framework of activity theory : a case study in an instructional design course
Karakuş, Türkan; Çağıltay, Kürşat; Department of Computer Education and Instructional Technology (2011)
Contextual issues have considerable role on learning outcomes of instructional design process. In this dissertation study, an instructional multimedia design and development course was explored to understand how contextual issues influence the experience and processes of Novice Instructional Designers’ (NIDs) activities in an instructional design project. The main participants of the study were 47 junior Computer Education and Instructional Technology students who were enrolled in the course. Besides, 26 st...
Visual Object Tracking with Autoencoder Representations
Besbinar, Beril; Alatan, Abdullah Aydın (2016-05-19)
Deep learning is the discipline of training computational models that are composed of multiple layers and these methods have recently improved the state of the art in many areas as a virtue of large labeled datasets, increase in the computational power of current hardware and unsupervised training methods. Although such a dataset may not be available for lots of application areas, the representations obtained by the well-designed networks that have a large representation capacity and trained with enough dat...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
F. Ç. Akyön, D. Çavuşoğlu, C. Cengiz, S. O. Altinuç, and A. Temizel, “Automated question generation and question answering from Turkish texts,”
Turkish Journal of Electrical Engineering and Computer Sciences
, vol. 30, no. 5, pp. 1931–1940, 2022, Accessed: 00, 2023. [Online]. Available: https://hdl.handle.net/11511/101785.