Natural Language Processing and Text Mining, Spring 2025 (Undergraduates)

This course offers an introduction to the concepts in natural language processing and the applications in text mining. This is offered as an elective course in the undergraduate program.

Course Information

Instructor: Jenq-Haur Wang
E-mail: jhwang AT <the domain for our school>
Office: R1534, Technology Building, ext. 4238
Office Hours: Tue & Fri. 9:10-12:00am
Class Hours: Tue. 15:10-17:00pm, Thu. 10:10-11:00am, R725, Sixth Teaching Building/R203, Pioneer Building
TA: Mr. Wang (R1424, Technology Building)
Textbook:
- Dan Jurafsky and James H. Martin. Speech and Language Processing (3rd ed. draft)
- Online draft available at: https://web.stanford.edu/~jurafsky/slp3/
- Current edition of the draft: Jan. 12, 2025
References:
- Chris Manning and Hinrich Schütze, Foundations of Statistical Natural Language Processing, MIT Press. Cambridge, MA: May 1999.

Latest News

Apr. 21, 2025: [NOTE] The midterm exam will be held on Apr. 22, 2025 at R725, Sixth Teaching Building. It will be open-book, but you cannot use any electronic devices.
Apr. 15, 2025: [NOTE] HW#2 has been announced.
Mar. 19, 2025: [NOTE] HW#1 has been announced.
Feb. 16, 2025: The homepage for Natural Language Processing and Text Mining (Spring 2025, Undergraduates) has been set up.

Tentative Schedule

NOTE: The tentative schedule and the slides are subject to changes.

Week	Date	Content	Homework
1	Feb. 18 & 20, 2025	Course Overview
2	Feb. 25 & 27, 2025	Introduction to NLP Ch.2 - Text processing
3	Mar. 4 & 6, 2025	Ch.2 - Edit Distance
4	Mar. 11 & 13, 2025	Ch.3, N-gram Language models
5	Mar. 18 & 20, 2025	Ch.4, Naive Bayes, Text Classification, and Sentiment	HW#1
6	Mar. 25 & 27, 2025	Ch.5, Logistic Regression
7	Apr. 1 & 3, 2025	Ch.6, Vector semantics and embeddings (4/3: Compensation Leave for Children's Day & Tomb Sweeping Day)	Due: HW#1
8	Apr. 8 & 10, 2025	Ch.17, Sequence labeling for POS and NER (introduction only)
9	Apr. 15 & 17, 2025	Ch.7, Neural language models	HW#2
10	Apr. 22 & 24, 2025	(4/22: Midterm Exam -- Ch.1-7, 17)	Term project proposal
11	Apr. 29 & May 1, 2025	Ch.8, RNNs & LSTMs (introduction only) Ch.9, Transformers (introduction only)	Due: HW#2 4/29 Due: Term project proposal
12	May 6 & 8, 2025	Ch.10, Large Language Models (introduction only)
13	May 13 & 15, 2025	Introduction to Text Mining Phrase mining
14	May 20 & 22, 2025	Named Entity Recognition (NER)	HW#3
15	May 27 & 29, 2025	Pattern-based text mining
16	Jun. 3 & 5, 2025	Term project presentation	Due: HW#3
17	Jun. 10 & 12, 2025	Term project presentation
18	Jun. 17 & 19, 2025	Term project presentation

Homework Assignments

Please hand in your homework in paper form or in electronic files before deadline.
Programs or homework in electronic files must be submitted to me via our submission site as follows:

Program Submission Site: iSchool+
User Account: your account in Taipei Tech Portal
Program Uploading: Please compress source codes and documentation in a .zip file, and clearly name your program files.
Note: If your program needs special environment or tool to compile or run, please write documentation about it.

There will be around 3-4 homeworks during this semester.

HW#1: Sentiment classification
Due: Apr. 1, 2025
HW#2: Similarity estimation using Word embeddings
Due: Apr. 29, 2025
HW#3: Named Entity Recognition

If you have any questions about the homework, please contact with the TA and me via e-mail.

Exams

Midterm Exam: Apr. 14 - 18, 2025.
- Date: Apr. 22, 2025
- Time: 15:10-17:00pm
- Location: R725, Sixth Teaching Building
- Range: Ch.1-7, 17
Final Exam: Jun. 16 - 20, 2025.

There will be no final exam for this course. Instead, we have the term project presentation in the last two to three weeks.

Score

E-mail: jhwang AT <the domain for our school>
Created: Feb. 16, 2025.
Last Updated: Apr. 21, 2025.