Type of Credit: Elective
Credit(s)
Number of Students
此課程將著重於簡介語言學如何應用於計算語言學領域，講課內容包含基本理論及大量實作練習。希望學生能於課程結束之後，能自行運用常見機器學習模組 (e.g., SVM, MaxEnt, RNN, LSTM, ELMO, BERT 等) 做相關語言學研究。此門課期待學生已有基本 python 程式基礎，以便於能於課程中直接做應用練習。(每週需自行攜帶筆電至課堂)
能力項目說明
期望學生能於修習課程後，對於機器學習模型有個大概了解，以及語言學相關研究能知道如何透過這些模型做出應用，於之後畢業論文撰寫或是至業界找相關工作時能有基礎知識。
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
(暫定)
*課程內容與指定閱讀、教學活動與作業等相關活動將於開學前提供 (每週需自行攜帶筆電至課堂)
週次 課程主題 學習投入時數
week 1 Course Introduction 5+
week 2 N-gram and language model 5+
week 3 Naive bayes, model training and evaluation 5+
week 4 Logistic regression and gradient descent 5+
week 5 Embeddings and weightings 5+
week 6 Basic neural networks 5+
week 7 Sequence labeling (HMM and CRF) 5+
week 8 Deep learning (RNN, LSTM, Transformers) 5+
week 9 Machine translation 5+
week 10 Transfer learning 5+
week 11 Discourse coherence 5+
week 12 Question answering 5+
week 13 Chatbots and dialogue systems 5+
week 14 Project Discussion 5+
week 15 Final Presentation 5+
week 16 Term Paper Due 5+
(暫定)
評分方式:
- 出席 20%
- 課堂練習/作業: 20%
- 課堂報告: 20%
- 期末口頭發表: 20%
- 期末報告: 20%
– Dan Jurafsky and James H. Martin. (2018). Speech and Language
Processing (3rd edition). Available at: https://web.stanford.edu/~jurafsky/slp3/.
– Benjamin Bengfort, Tony Ojeda and Rebecca Bilbro. (2018). Applied Text Analysis with Python: enabling language-aware data products with machine learning. O’Reilly.
– Jacob Perkins, Nitin Hardeniya, Deepti Chopra, Nisheeth Joshi and Iti Mathur. (2016). Natural Language Processing: Python
and NLTK. O’Reilly.
– Mark Lutz. (2015). Learning Python (5th edition). O’Reilly.
– Ruslan Mitkov. (2014). The Oxford Handbook of Computational Linguistics (2nd edition). Oxford University Press.
– Chris Manning and Hinrich Schütze. (1999). Foundations of Statistical Natural Language Processing. MIT Press.