English grammar multiple-choice question generation using Text-to-Text Transfer Transformer
English grammar multiple-choice questions (MCQs) can be automatically generated to reduce preparation time. Previous studies have focused on semiautomated methods based on the transformation of human-made sentences/articles into MCQs, owing to which the number of generated questions is dependent on...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Computers and Education: Artificial Intelligence |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666920X23000371 |
| _version_ | 1797383638075047936 |
|---|---|
| author | Peerawat Chomphooyod Atiwong Suchato Nuengwong Tuaycharoen Proadpran Punyabukkana |
| author_facet | Peerawat Chomphooyod Atiwong Suchato Nuengwong Tuaycharoen Proadpran Punyabukkana |
| author_sort | Peerawat Chomphooyod |
| collection | DOAJ |
| description | English grammar multiple-choice questions (MCQs) can be automatically generated to reduce preparation time. Previous studies have focused on semiautomated methods based on the transformation of human-made sentences/articles into MCQs, owing to which the number of generated questions is dependent on the size of a given text corpus. This study proposes an artificial intelligence-assisted MCQ generation system that increases the number of generable questions using controllable text generation techniques. In this system, the questions for MCQs are generated using a text generation model trained using the Text-to-Text Transfer Transformer (T5) architecture, a powerful deep learning model for performing text generation tasks, with a keyword and a part-of-speech (POS) template as the input for content and grammar topic control. For the text-to-MCQ transformation process, answer-to-MCQ and distractor-selection strategies are proposed for 10 grammar topics using rule-based algorithms. The quality of the generated MCQs is evaluated by human experts. The acceptance rate of the questions generated using the proposed system is 86%. The controllability of content and grammar topics are 96.86% and 98.57%, respectively. The findings of this study show that the T5 model achieves good performance in terms of controlling the POS structure in a keyword-to-text generation task. Moreover, the good acceptance rate indicates that artificial intelligence has the potential to help teachers speed up the process of selecting examination questions. We also discuss extending the proposed system to other grammar topics and the limitations of the proposed system. |
| first_indexed | 2024-03-08T21:23:57Z |
| format | Article |
| id | doaj.art-1c2e9177bd4c4623aea067d0df29950f |
| institution | Directory Open Access Journal |
| issn | 2666-920X |
| language | English |
| last_indexed | 2024-03-08T21:23:57Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computers and Education: Artificial Intelligence |
| spelling | doaj.art-1c2e9177bd4c4623aea067d0df29950f2023-12-21T07:37:59ZengElsevierComputers and Education: Artificial Intelligence2666-920X2023-01-015100158English grammar multiple-choice question generation using Text-to-Text Transfer TransformerPeerawat Chomphooyod0Atiwong Suchato1Nuengwong Tuaycharoen2Proadpran Punyabukkana3Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Road, Pathumwan, Bangkok 10330, ThailandCorresponding authors.; Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Road, Pathumwan, Bangkok 10330, ThailandDepartment of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Road, Pathumwan, Bangkok 10330, ThailandCorresponding authors.; Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Phayathai Road, Pathumwan, Bangkok 10330, ThailandEnglish grammar multiple-choice questions (MCQs) can be automatically generated to reduce preparation time. Previous studies have focused on semiautomated methods based on the transformation of human-made sentences/articles into MCQs, owing to which the number of generated questions is dependent on the size of a given text corpus. This study proposes an artificial intelligence-assisted MCQ generation system that increases the number of generable questions using controllable text generation techniques. In this system, the questions for MCQs are generated using a text generation model trained using the Text-to-Text Transfer Transformer (T5) architecture, a powerful deep learning model for performing text generation tasks, with a keyword and a part-of-speech (POS) template as the input for content and grammar topic control. For the text-to-MCQ transformation process, answer-to-MCQ and distractor-selection strategies are proposed for 10 grammar topics using rule-based algorithms. The quality of the generated MCQs is evaluated by human experts. The acceptance rate of the questions generated using the proposed system is 86%. The controllability of content and grammar topics are 96.86% and 98.57%, respectively. The findings of this study show that the T5 model achieves good performance in terms of controlling the POS structure in a keyword-to-text generation task. Moreover, the good acceptance rate indicates that artificial intelligence has the potential to help teachers speed up the process of selecting examination questions. We also discuss extending the proposed system to other grammar topics and the limitations of the proposed system.http://www.sciencedirect.com/science/article/pii/S2666920X23000371Multiple-choice questionAutomatic question generationArtificial intelligence–based learningLanguage learningEducation technology |
| spellingShingle | Peerawat Chomphooyod Atiwong Suchato Nuengwong Tuaycharoen Proadpran Punyabukkana English grammar multiple-choice question generation using Text-to-Text Transfer Transformer Computers and Education: Artificial Intelligence Multiple-choice question Automatic question generation Artificial intelligence–based learning Language learning Education technology |
| title | English grammar multiple-choice question generation using Text-to-Text Transfer Transformer |
| title_full | English grammar multiple-choice question generation using Text-to-Text Transfer Transformer |
| title_fullStr | English grammar multiple-choice question generation using Text-to-Text Transfer Transformer |
| title_full_unstemmed | English grammar multiple-choice question generation using Text-to-Text Transfer Transformer |
| title_short | English grammar multiple-choice question generation using Text-to-Text Transfer Transformer |
| title_sort | english grammar multiple choice question generation using text to text transfer transformer |
| topic | Multiple-choice question Automatic question generation Artificial intelligence–based learning Language learning Education technology |
| url | http://www.sciencedirect.com/science/article/pii/S2666920X23000371 |
| work_keys_str_mv | AT peerawatchomphooyod englishgrammarmultiplechoicequestiongenerationusingtexttotexttransfertransformer AT atiwongsuchato englishgrammarmultiplechoicequestiongenerationusingtexttotexttransfertransformer AT nuengwongtuaycharoen englishgrammarmultiplechoicequestiongenerationusingtexttotexttransfertransformer AT proadpranpunyabukkana englishgrammarmultiplechoicequestiongenerationusingtexttotexttransfertransformer |