於一企業之產品研發專案中，負責該專案之專案工程師往往需事先閱讀大量技術文件，並將研發人員所撰寫之技術文件內容轉化為更簡潔的表達方式，以利高階管理者有效瞭解專案內容。然而，技術文件通常包含許多技術性用語，由於研發人員與專案工程師之專業領域不同，專案工程師往往難以快速且準確地將研發人員所撰寫之技術文件內容轉化為較簡潔的表達方式。此外，專案工程師需耗費時間及精力閱讀大量技術文件，並判定此些文件內容的資訊豐富程度及易讀程度，才能將技術文件轉化為審查此專案之主管或其他閱讀者易於解讀的說明資料。為解決前述問題，本研究乃發展一套「依讀者角色提升文件內容易讀性之技術文件內容轉化」模式，以協助專案工程師有效地將技術文件轉化為高階管理者或其他閱讀者易於解讀的說明資料，進而協助高階管理者或其他非相關技術背景人士理解原技術文件之內容重點。
本研究所提出之「依讀者角色提升文件內容易讀性之技術文件內容轉化」模式可分為「技術內容及其所對應之廣告內容解析」前置階段及「目標技術文件內容轉化」方法論。於「技術內容及其所對應之廣告內容解析」前置階段，本研究乃先釐清各類產品相關之技術內容及廣告內容中的技術特徵，並解析各特徵內容於技術內容及廣告內容中之表達方式。以前述過程之結果為基礎，本研究歸納各特徵內容由技術內容轉化為廣告內容之轉化原則，以利後續方法論可藉由此些原則轉化目標技術內容。之後，本研究乃利用類神經網路方法建立技術資訊密度影響因子及技術資訊密度值之關聯模型，以利後續藉由此關聯模型分析目標技術內容之資訊豐富程度。而「目標技術文件內容轉化」方法論乃擷取目標技術內容所包含的技術特徵值，並利用前置階段所建立之關聯模型推估目標技術內容的技術資訊密度值。之後，此模式提供目標技術內容之資訊豐富程度的分析結果及技術特徵表達方式的轉化建議，並將此些資訊以視覺化方式呈現，以協助專案工程師有效地將技術文件轉化為高階管理者或其他閱讀者易於解讀的說明資料。

The project engineer who is responsible for a product development project often needs to read the technical documents written by research and development (R&D) engineers and convert the technical content into concise and easily interpretable content. However, due to the different professional domains between R&D engineers and project engineers, the latter often struggle to efficiently and accurately convert the technical content into concise and easily interpretable content. Additionally, the project engineer has to invest time and effort in reading numerous technical documents and enhancing the readability of these documents. In order to solve the above problems, this study develops a “Readability Enhancement and Content Conversion” model. The proposed model extracts the key information from technical documents and utilizes the neural network to assess the readability of technical documents. After that, the proposed model provides recommendations for converting the technical content in order to enhance the readability of technical content. Furthermore, the proposed model visualizes the key information and the content readability analysis results. Based on the proposed model, the project engineer can effectively convert the technical content into concise and easily interpretable content.

摘要 I
ABSTRACT II
目錄 III
圖目錄 V
表目錄 VII
第一章、研究背景 1
1.1研究動機與目的 1
1.2研究步驟 4
1.3研究定位 8
第二章、文獻回顧 11
2.1「文件內容之特徵值擷取」議題 11
2.2「文件內容之易讀性評估」議題 20
2.3「文件內容轉化」議題 23
第三章、依讀者角色提升文件內容易讀性之技術文件內容轉化模式 27
3.1技術內容及廣告內容之技術特徵解析 28
3.2目標技術內容之技術資訊密度值推論及技術特徵值擷取 68
3.3技術文件內容之轉化建議與重點彙整 84
第四章、系統開發與績效驗證 106
4.1「技術文件之資訊豐富度分析暨內容轉化」系統之執行過程與結果 106
4.2模式與系統之驗證方式 110
4.3模式與系統之驗證結果 114
第五章、結論與未來展望 144
5.1論文總結 145
5.2未來展望 147
參考文獻 149
附錄A、技術內容及廣告內容解析 152
附錄B、模式之績效驗證資料 165
附錄C、模式之績效驗證結果 177
附錄D、「技術內容之技術特徵值擷取」議題之問卷 338
附錄E、「技術內容之技術特徵值擷取」議題之問卷 349

1.Armouty, B. and Tedmori, S., 2019, “Automated Keyword Extraction Using Support Vector Machine from Arabic News Documents,” 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, pp. 342-346.
2.Barros, F., Silva, E., Prudêncio, R., Filho, V. and Nascimento, A., 2008, “Hidden Markov Models and Text Classifiers for Information Extraction on Semi-Structured Texts,” 2008 Eighth International Conference on Hybrid Intelligent Systems, pp. 417-422.
3.Çavusoğlu, D., Dayibasi, O. and Sağlam, R.-B., 2018, “Key Extraction in Table Form Documents: Insurance Policy as an Example,” 2018 3rd International Conference on Computer Science and Engineering, pp. 195-200.
4.Çelikten, A., Uğur, A. and Bulut, H., 2021, “Keyword Extraction from Biomedical Documents Using Deep Contextualized Embeddings,” 2021 International Conference on Innovations in Intelligent Systems and Applications, pp. 1-5.
5.Chagheri, S., Roussey, C., Calabretto, S. and Dumoulin, C., 2011, “Technical Documents Classification,” Proceedings of the 2011 15th International Conference on Computer Supported Cooperative Work in Design, pp. 808-812.
6.Chaudary, A., Nasar, Z., Mubasher, M. and Qounain, S., 2020, “Extraction of Useful Information from Crude Job Descriptions,” 2020 IEEE 23rd International Multitopic Conference, pp. 1-4.
7.Chen, Y.-H. and Lin, T.-C., 2014, “Dimension Reduction Techniques for Accessing Chinese Readability,” 2014 International Conference on Machine Learning and Cybernetics, pp. 434-438.
8.Daowadung, P. and Chen, Y.-H., 2008, “Using Word Segmentation and SVM to Assess Readability of Thai Text for Primary School Students,” 2011 Eighth International Joint Conference on Computer Science and Software Engineering, pp. 170-174.
9.Gooding, S. and Kochmar, E., 2019, “Recursive Context-Aware Lexical Simplification,” Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 4853-4863.
10.Heni, S., Ejbali, R., Zaied, M. and Amar, C.-B., 2011, “A Neural Principal Component Analysis for Text Based Documents Keywords Extraction,” 2011 3rd International Conference on Next Generation Networks and Services, pp. 112-115.
11.Imperial, J.-M., Roxas, R.-E., Campos, E.-M., Oandasan, J., Caraballo, R., Sabdani, F.-W. and Almaroi, A.-R., 2019, “Developing a Machine Learning-based Grade Level Classifier for Filipino Children’s Literature,” 2019 International Conference on Asian Language Processing, pp. 413-418.
12.Karmakar, S. and Zhu, Y., 2010, “Visualizing Text Readability,” 2010 6th International Conference on Advanced Information Management and Service, pp. 291-296.
13.Kauchak, D., Mouradi, O., Pentoney, C. and Leroy, G., 2014, “Text Simplification Tools: Using Machine Learning to Discover Features that Identify Difficult Text,” 2014 47th Hawaii International Conference on System Sciences, pp. 2616-2625.
14.Kavila, S.-D., Rajesh, B., Vyshnavi, N. and Sushma, K.-M., 2017, “Automatic Key Term Extraction from Research Article using Hybrid Approach,” International Journal of Computer Applications, Vol. 166, pp. 17-21.
15.Nigusie, G. and Asfaw, T.-T., 2022, “Lexical Complexity Detection and Simplification in Amharic Text Using Machine Learning Approach,” 2022 International Conference on Information and Communication Technology for Development for Africa, pp. 78-83.
16.Oelke, D., Spretke, D. Stoffel, A. and Keim, D.-A., 2010, “Visual Readability Analysis: How to Make Your Writings Easier to Read,” 2010 IEEE Symposium on Visual Analytics Science and Technology, pp. 123-130.
17.Proulx, J., Kandula, S., Hill, B. and Zeng-Treitler, Q., 2013, “Creating Consumer Friendly Health Content: Implementing and Testing a Readability Diagnosis and Enhancement Tool,” 2013 46th Hawaii International Conference on System Sciences, pp. 2445-2453.
18.Smith, L.-N., 2018, “A Disciplined Approach to Neural Network Hyper-Parameters,” arXiv: Learning, pp. 1-21.
19.Sun, G., Jiang, Z., Gu, Q. and Chen, D., 2014, “Linear Model Incorporating Feature Ranking for Chinese Documents Readability,” The 9th International Symposium on Chinese Spoken Language Processing, pp. 29-33.
20.Takano, K., Tanaka, M., Sakai, H., Kitajima, R., Ota, T., Tanabe, C. and Sakaji, H., 2019, “Extraction of Characteristic Terms from Patent Documents for Technical Trend Analysis,” 2019 8th International Congress on Advanced Applied Informatics, pp. 667-672.
21.Wang, Y., Luo, S., Hu, Z. and Han, M., 2018, “A Study of Event Elements Extraction on Chinese Bond News Texts,” 2018 IEEE International Conference on Progress in Informatics and Computing (PIC), pp.420-424.
22.Wang, Y., Qi, J., Lei, L. and Zheng, K., 2018, “A CNN-based Feature Extraction Scheme for Patent Analysis,” 2018 IEEE 4th International Conference on Computer and Communications, pp. 2387-2391.
23.Wibowo, M.-S., Romadhony, A. and Sa’adah, S., 2019, “Lexical and Syntactic Simplification for Indonesian Text,” 2019 International Seminar on Research of Information Technology and Intelligent Systems, pp. 64-68.
24.Yang, S. and Yang, F., 2021, “Chinese Automatic Text Simplification Based on Unsupervised Learning,” 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference, pp. 1666-1672.
25.Yu, F., Xuan, H. and Zheng, D., 2012, “Key-Phrase Extraction Based on a Combination of CRF Model with Document Structure,” 2012 Eighth International Conference on Computational Intelligence and Security, pp. 406-410.