請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89046
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 張瑞益 | zh_TW |
dc.contributor.advisor | Ray-I Chang | en |
dc.contributor.author | 許荃伊 | zh_TW |
dc.contributor.author | Chuan-Yi Hsu | en |
dc.date.accessioned | 2023-08-16T16:54:23Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-08-16 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-08-07 | - |
dc.identifier.citation | [1] ChatGPT, response to author query. OpenAI [Online]. https://chatgpt.pro/ (accessed February 15, 2023).
[2] 臺中教育大學. "臺灣兒童手寫英文作業." National Taichung University of Education (accessed. [3] L. C. a. colleagues, "Lower Elementary (Ages 6) Writing Samples," 2014 [4] C. C. Tappert, C. Y. Suen, and T. Wakahara, "The state of the art in online handwriting recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 787-808, 1990, doi: 10.1109/34.57669. [5] Z. Q. Zhao, P. Zheng, S. T. Xu, and X. Wu, "Object Detection With Deep Learning: A Review," IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, 2019, doi: 10.1109/TNNLS.2018.2876865. [6] R. Girshick, "Fast r-cnn," in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440-1448. [7] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal loss for dense object detection," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980-2988. [8] W. Liu et al., "Ssd: Single shot multibox detector," in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 2016: Springer, pp. 21-37. [9] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788. [10] J Glenn Jocher, “ultralytics/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration”. Zenodo, Jan. 05, 2021. doi: 10.5281/zenodo.4418161. [11] B. Shi, X. Bai, and C. Yao, "An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 11, pp. 2298-2304, 2016. [12] C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9. [13] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. [14] J. L. Elman, "Finding structure in time," Cognitive science, vol. 14, no. 2, pp. 179-211, 1990. [15] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997, doi: 10.1162/neco.1997.9.8.1735. [16] A. Vaswani et al., "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017. [17] K. Weiss, T. M. Khoshgoftaar, and D. Wang, "A survey of transfer learning," Journal of Big data, vol. 3, no. 1, pp. 1-40, 2016. [18] A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, "Improving language understanding by generative pre-training," 2018. [19] R. Lennon, "TranscriptFixer 1.0," 2023, [Online]. https://doc.clickup.com/42042215/d/h/1830v7-940/15efb9246a198ba/1830v7-2120. [20] D. P. HARDMAN, "ChatGPT for Educators," 2023, [Online]. https://drphilippahardman.substack.com/p/chatgpt-prompt-engineering-for-educators. [21] D. P. HARDMAN, "Introducing: ChatGPT Edu-Mega-Prompts," 2023, [Online]. https://drphilippahardman.substack.com/p/introducing-chatgpt-edu-mega-prompts [22] Tzutalin, “LabelImg.” 2015. [23] P.-C. Chen, "Traditional Chinese Handwriting Dataset," GitHub repository, 2020. [Online]. Available: https://github.com/AI-FREE-Team/Traditional-Chinese-Handwriting-Dataset. [24] U. M. a. H. Bunke, "The IAM-database: An English Sentence Database for Off-line Handwriting Recognition," Document Analysis and Recognition, vol. 5, pp. 39 - 46, 2002. [25] J. Huang et al., "A multiplexed network for end-to-end, multilingual OCR," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4547-4557. [26] J. Hu, L. Shen, and G. Sun, "Squeeze-and-Excitation Networks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132-7141, 2017. [27] K. a. Z. He, Xiangyu and Ren, Shaoqing and Sun, Jian, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016. [28] A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, "Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks," presented at the Proceedings of the 23rd international conference on Machine learning, Pittsburgh, Pennsylvania, USA, 2006. [Online]. Available: https://doi.org/10.1145/1143844.1143891. [29] S. Vijayarani and A. Sakila, "Performance comparison of OCR tools," International Journal of UbiComp (IJU), vol. 6, no. 3, pp. 19-30, 2015. [30] J. J. "ChatGPT API Transition Guide - How to get started." OpenAI. https://help.openai.com/en/articles/7042661-chatgpt-api-transition-guide (accessed. [31] OpenAI, "How to format inputs to ChatGPT models," 2023, [Online]. https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89046 | - |
dc.description.abstract | 本研究旨在使用ChatGPT開發一個針對教育領域的臺灣兒童手寫英文作業批改系統與提示(Prompt)平台,主要目標是提供教師在批改作業和設計提示方面的交流。本系統採用遷移式學習和人工監督的方式解決資料稀缺的問題,並利用光學字元辨識 (Optical Character Recognition, OCR) 技術辨識台灣兒童手寫作業及使用 ChatGPT 提供即時的批改建議,以提升教師作業批改的效率。
此外,本系統也建立了一個提示平台,提供教師們分享和討論自行設計的提示,以促進教師之間的交流與共享,透過這樣的提示平台,旨在收集豐富且多樣的提示資源,同時鼓勵教師積極接受這些便利的科技工具,將其應用於教學實踐中,並教導學生如何正確地運用這些便利科技。 經過實驗結果顯示,本系統能夠有效地協助教師進行作業批改,同時促進教師之間的提示交流和共享,對於提高教師的作業批改效率,收集多樣的提示資源以及鼓勵教師運用這些便利科技在教學中發揮作用具有重要意義。 | zh_TW |
dc.description.abstract | This study aims to develop a Taiwan Children's Handwritten English Assignment Correction System and Prompt Platform for the educational field by ChatGPT. The main objective of this system is to provide support for teachers in the aspects of assignment correction and prompt design communication. In this study, transfer learning and manual supervision were employed to address the issue of data scarcity. Optical Character Recognition (OCR) was utilized to recognize Taiwan children's handwritten assignments, and ChatGPT provided real-time correction suggestions, enhancing the efficiency of teachers' assignment correction.
Furthermore, this system establishes a prompt platform for teachers to share and discuss their own designed prompts, promoting communication and sharing among teachers. Through this prompt platform, we aim to gather rich and diverse prompt resources while encouraging teachers to actively embrace these convenient technological tools and apply them in their teaching practices, as well as teaching students how to correctly utilize these convenient technologies. Experimental results have shown that our system effectively assists teachers in assignment correction while facilitating communication and sharing among teachers. This research holds significant importance in improving teachers' assignment correction efficiency, collecting diverse prompt resources, and encouraging teachers to utilize these convenient technologies in their teaching practices. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-16T16:54:23Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-08-16T16:54:23Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 致謝 i
中文摘要 ii ABSTRACT iii 目錄 iv 圖目錄 vi 表目錄 viii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 1 1.3 研究目的 3 第二章 文獻探討 4 2.1 目標偵測與光學字元辨識 4 2.2 遷移式學習 4 2.3 ChatGPT 5 2.4 提示工程 6 第三章 系統設計 8 3.1 系統總攬 8 3.2 臺灣兒童手寫英文批改 8 3.2.1 臺灣兒童手寫英文批改案例使用說明 10 3.3 提示平台 14 3.3.1 提示平台案例使用說明 15 第四章 功能實作 21 4.1 臺灣兒童手寫英文批改系統 21 4.1.1 資料集 21 4.1.2 訓練 YOLO 辨識手寫字區域 22 4.1.3 訓練 OCR 辨識臺灣兒童手寫字 22 4.1.4 ChatGPT Prompt 24 4.1.5 模擬學生使用臺灣兒童手寫英文批改系統流程 27 4.2 提示平台 28 4.2.1 訊問資料正確性 28 4.2.2 提示搜尋功能 29 4.2.3 提示測試功能 30 4.2.4 提示設計功能 31 4.2.5 模擬教師使用提示平台流程 32 第五章 結果與討論 35 5.1 ChatGPT 效能 35 5.2 提示工程的發現 35 5.3 提示平台的需要 38 第六章 結論與未來展望 39 6.1 結論 39 6.2 未來展望 39 REFERENCE 41 | - |
dc.language.iso | zh_TW | - |
dc.title | 使用ChatGPT之臺灣兒童手寫英文批改與其提示平台設計 | zh_TW |
dc.title | Applying ChatGPT for Taiwan Children’s Handwritten English Correction and its Prompt Platform Design | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 張恆華;王家輝;張信宏 | zh_TW |
dc.contributor.oralexamcommittee | Heng-Hua Chang;Chia-Hui Wang;Shin-Hung Chang | en |
dc.subject.keyword | 深度學習,光學字元辨識,提示工程,ChatGPT, | zh_TW |
dc.subject.keyword | Deep learning,Optical Character Recognition,Prompt engineering,ChatGPT, | en |
dc.relation.page | 42 | - |
dc.identifier.doi | 10.6342/NTU202303494 | - |
dc.rights.note | 未授權 | - |
dc.date.accepted | 2023-08-10 | - |
dc.contributor.author-college | 工學院 | - |
dc.contributor.author-dept | 工程科學及海洋工程學系 | - |
顯示於系所單位: | 工程科學及海洋工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 目前未授權公開取用 | 2.46 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。