藉助線上課程之自動結構化、分類與理解以提升學習效率

More Efficient Learning by Structuring, Classifying and Understanding Lectures in Online Courses

沈昇勳(Sheng-Syun Shen)

指導教授 ： 李琳山

國立臺灣大學/電機資訊學院/電信工程學研究所/碩士(2016年)

https://doi.org/10.6342/NTU201603472

摘要

近年來線上課程平台發展日益蓬勃，諸如Cousera、edX等線上課程網站均大受歡迎，因此線上課程漸漸成為學習知識的一項重要途徑。在這些學習平台上，充滿著各類型的課程供使用者選擇，其內容之多、主題分佈之廣，儼然就是一個多元豐富架構完整的知識網。不同於傳統學習知識的途徑與媒介，線上課程平台缺乏與授課教師面對面互動的機會，而此一不同或多或少對使用者的學習造成一些限制。
本論文旨在研發建構一個更完整的線上課程平台所需的各項輔助學習相關技術，希望能夠輔助線上課程平台的使用者，讓他們在學習時有更多資訊可更方便有效率的學習。這些技術包括課程內與課程間的教材結構化，在課程內就投影片上的文字與教師講課的語音內容進行連結，也在內容相關的課程之間建立連結或先後關係。為讓使用者能夠更方便地檢索他想查詢的課程，本論文亦研究能將課程依照內容主題進行分類的技術。此外，本論文亦研究了就語音數位內容進行語意理解的可能，期許未來機器能夠自行聽懂課程內容，更有機會可以為使用者進行更多提升學習效率的有關分析。

關鍵字

線上課程 ； 深層學習 ； 語意理解 ； 支撐向量機

並列摘要

The increasing popularity of Massive Open Online Courses (MOOCs) has resulted in a huge number of courses available over the Internet under various MOOCs platforms such as edX and Coursera. The wide variety and efficiency of such courses has offered great convenience to learners. However, it is still relatively inconvenient for some learners for lack of face-to-face interactions with lecturers in such platforms.
Considering the above problem, this thesis aims at creating a set of new technologies for a comprehensive online learning platform, which could help users to learn more efficiently. This platform includes such functionalities as the following: structuring the lectures, within a course and across many courses, extracting the key term sets for better classifying the lectures, and machine understanding on the lectures. Lecture structuring includes not only the alignment between slide contents and spoken utterances within a course, but also providing the connections and prerequisite relationships between courses. Besides, automatically extracted key term sets for the lectures offer a better way for users to retrieve exactly the desired lectures. This thesis also conducts studies on machine understanding on the lectures, hoping to improve the learning scenario in the future.

並列關鍵字

Massive Open Online Courses ； Deep Learning ； Natural Language Understanding ； Support Vector Machine

參考文獻

[3] Klaus Ries, “Hmm and neural network based speech act detection,” in Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on. IEEE, 1999, vol. 1, pp. 497–500.

[8] Huijuan Xu and Kate Saenko, “Ask, attend and answer: Exploring question-guided spatial attention for visual question answering,” arXiv preprint arXiv:1511.05234, 2015.

[9] Geoffrey E Hinton, Simon Osindero, and Yee-Whye Teh, “A fast learning algorithm for deep belief nets,” Neural computation, vol. 18, no. 7, pp. 1527–1554, 2006.

[10] T Mikolov and J Dean, “Distributed representations of words and phrases and their compositionality,” Advances in neural information processing systems, 2013.

[14] Jeffrey Pennington, Richard Socher, and Christopher D Manning, “Glove: Global vectors for word representation.,” in EMNLP, 2014, vol. 14, pp. 1532–43.