臺灣博碩士論文加值系統

近幾年有關人工智慧與機器學習相關領域蓬勃發展，人機互動介面也變得更加智慧化，應用包含語音助理、對話情境分析、文章段落分析等，而這些應用的基礎來自於機器學習中的子領域「自然語言處理」。
本論文首先介紹近代語言學發展，之後進一步分析字詞與句法架構，接著介紹近年來受歡迎的自然語言處理工具以及演算法，並實際應用此工具及演算法，設計一個人機互動應用程式，再依照程式的執行結果，分析此程式的優缺點。

With the rapid development of information technology and networks. The need for computers to deal with natural language becomes more and more urgent. Natural language processing in addition to data searching and data mining. In recent years, a large number of human-computer interaction interfaces, have been widely used. However, in the actual research of natural language processing, the system structure used has become more and more complex. But it's still from the Chinese grammar. Like words, part of speech, and analysis of conversational situations.
In this thesis, we introduce the development of Chinese linguistics.
Afterwards, analysis of Chinese words and syntactic structures. Next, we introduce natural language processing tools and algorithms that are quite popular in recent years. And use these tools, design a simple chatbot. Analyze the advantages and disadvantages of this tool and algorithm.

摘要 i
ABSTRACT ii
目錄 iii
圖目錄 iv
第一章、研究背景與動機 1
第二章、現代語言學發展 2
2.1現代自然語言系統簡介 2
2.2語句發展 2
2.3語義研究 4
第三章、自然語言處理工具 6
3.1中文語言處理架構 6
3.2常見的自然語言處理系統 7
第四章、自然語言常見演算法簡介 12
第五章、實際應用與結果分析 14
第六章、結論 21
附錄 22
參考文獻 30

[1] 鄭捷, 自然語言處理：用人工智慧看懂中文,page 1-7, 2018, 佳魁資訊
[2] 馮冠, 倪寶童, 電腦網路標準教程, 清華大學出版社, 2010
[3] 同[1],page 2-32
[4] 同[1],page 2-43
[5] 同[1],page 1-9
[6] 語言雲, 語言技術平台, 哈工大社會計算與訊息檢索研究中心
https://www.ltp-cloud.com/
[7] The Stanford Natural Language Processing Group
https://nlp.stanford.edu/
[8] Natural Language Toolkit
https://www.nltk.org/
[9] 結巴中文分詞
https://github.com/fxsjy/jieba
[10] NLPIR-ICTCLAS漢語分詞系統
http://ictclas.nlpir.org/
[11] 漢語言處理包
https://github.com/hankcs/HanLP
[12] Norris, James R, Markov chains, Cambridge University Press, 1998.
[13] Lawrence R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications
in Speech Recognition, Proceedings of the IEEE, pp.257-286, February 1989.
[14] 演算法筆記- Hidden Markov Model
http://www.csie.ntnu.edu.tw/~u91029/HiddenMarkovModel.html