Automatic question generation with natural language processing
In Natural Language Processing (NLP), Automatic Question Generation (AQG) is an important task that involves generating human-comprehensible questions from an input text. There are many useful applications in AQG, notably in educational settings, to create quizzes or reading comprehension papers. Ma...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/157297 |
| _version_ | 1826126157584531456 |
|---|---|
| author | Tran, Thuy Dung |
| author2 | Andy Khong W H |
| author_facet | Andy Khong W H Tran, Thuy Dung |
| author_sort | Tran, Thuy Dung |
| collection | NTU |
| description | In Natural Language Processing (NLP), Automatic Question Generation (AQG) is an important task that involves generating human-comprehensible questions from an input text. There are many useful applications in AQG, notably in educational settings, to create quizzes or reading comprehension papers. Many techniques have been studied for AQG, from rule-based algorithms to complex deep learning networks. As machine learning advances, transformer-based neural networks are more robust than rule-based logic in generating questions without prior knowledge of the grammar rules. However, current state-of-the-art models still perform worse in paragraph-level texts than sentence-level inputs.
This FYP studies the pros and cons of different AQG methods in long paragraphs to design a multitasking model for AQG. By utilising transfer learning, this project’s best model is a robust AQG + summarisation T5 transformer, outperforming existing more complex Seq2seq and RNN models, achieving scores on BLEU-4 of 16.37, METEOR of 20.4, and ROUGE_L of 41.50. This project’s model does not require answer input, i.e., less information is given, but the performance is on par with many answer-aware models.
The effectiveness of different AQG methods is analysed. Then, the T5-based AQG transfer learning model pipeline is designed, and different training parameters (batch size, epochs, learning rate) are tuned to optimise performance. The model’s predictions are also evaluated against human-generated questions and compared with existing models. Finally, a full-stack React Web Application using the model is implemented to demonstrate its application as a Quiz Generator. |
| first_indexed | 2024-10-01T06:48:07Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/157297 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:48:07Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1572972023-07-07T19:05:21Z Automatic question generation with natural language processing Tran, Thuy Dung Andy Khong W H School of Electrical and Electronic Engineering AndyKhong@ntu.edu.sg Engineering::Electrical and electronic engineering::Computer hardware, software and systems Engineering::Computer science and engineering::Software::Software engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence In Natural Language Processing (NLP), Automatic Question Generation (AQG) is an important task that involves generating human-comprehensible questions from an input text. There are many useful applications in AQG, notably in educational settings, to create quizzes or reading comprehension papers. Many techniques have been studied for AQG, from rule-based algorithms to complex deep learning networks. As machine learning advances, transformer-based neural networks are more robust than rule-based logic in generating questions without prior knowledge of the grammar rules. However, current state-of-the-art models still perform worse in paragraph-level texts than sentence-level inputs. This FYP studies the pros and cons of different AQG methods in long paragraphs to design a multitasking model for AQG. By utilising transfer learning, this project’s best model is a robust AQG + summarisation T5 transformer, outperforming existing more complex Seq2seq and RNN models, achieving scores on BLEU-4 of 16.37, METEOR of 20.4, and ROUGE_L of 41.50. This project’s model does not require answer input, i.e., less information is given, but the performance is on par with many answer-aware models. The effectiveness of different AQG methods is analysed. Then, the T5-based AQG transfer learning model pipeline is designed, and different training parameters (batch size, epochs, learning rate) are tuned to optimise performance. The model’s predictions are also evaluated against human-generated questions and compared with existing models. Finally, a full-stack React Web Application using the model is implemented to demonstrate its application as a Quiz Generator. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-05-13T08:25:46Z 2022-05-13T08:25:46Z 2022 Final Year Project (FYP) Tran, T. D. (2022). Automatic question generation with natural language processing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157297 https://hdl.handle.net/10356/157297 en B3020-211 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering::Computer hardware, software and systems Engineering::Computer science and engineering::Software::Software engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Tran, Thuy Dung Automatic question generation with natural language processing |
| title | Automatic question generation with natural language processing |
| title_full | Automatic question generation with natural language processing |
| title_fullStr | Automatic question generation with natural language processing |
| title_full_unstemmed | Automatic question generation with natural language processing |
| title_short | Automatic question generation with natural language processing |
| title_sort | automatic question generation with natural language processing |
| topic | Engineering::Electrical and electronic engineering::Computer hardware, software and systems Engineering::Computer science and engineering::Software::Software engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/157297 |
| work_keys_str_mv | AT tranthuydung automaticquestiongenerationwithnaturallanguageprocessing |