CS372: Natural Language Processing with Python

Instructor

• Jong C. Park

• Email: jongpark@kaist.ac.kr

• Office: E3-1, Room 2406

• Phone: x3541

Teaching Assistants

• Aujin Kim (Head), Sukmin Cho, Eui jun Hwang

• Email: cs372@nlp.kaist.ac.kr

Lecture Hours and Rooms

• 14:30~16:00, Tuesdays and Thursdays

• Lectures on Tuesdays are Online, and Lectures on Thursdays are on E3-1101 (1강의실)

• (may be replaced by Online lectures, depending on the Covid-19 situations)

• The first lecture will be taken online

Exam Hours

• 13:00~15:45, Thursdays / E3-1101

Textbook

• S. Bird, E. Klein and E. Loper, Natural Language Processing with Python, O'Reilly, 2nd edition, 2010

• Will be based on up-to-date version available on the Internet (https://nltk.org)

Evaluation

• Attendance: 20%

  • • Class attendance: Zoom login history (on-line), class summary

    • Occasional quizzes and class interactions

• Exams and Homework: 50%

  • • Plan A

      • Midterm: 15% (4/21)

      • Final: 15% (6/16)

      • Homework: 20%

HW #1 (10%, ~4/8)

HW #2 (10%, ~5/6)

• • • Plan B

      • Homework: 50%
        HW #1 (10%, ~4/8)

HW #2 (15%, ~5/6)

HW #3 (25%, ~5/27)

• Project: 30%

  • • Proposal report (10%, ~5/13)

    • Final report (10%, ~6/3)

    • Final presentation (10%, 6/7 + 6/9)

  • Teamwork

    • Maximum of two students per team

    • One student per team is also allowed

• Grading will be A/B/C +/0/-.

Lecture Schedule

• Week 1: Language Processing and Python

• Week 2: Accessing Text Corpora and Lexical Resources

• Week 3: Processing Raw Text I

• Week 4: Processing Raw Text II

• Week 5: Writing Structured Programs

• Week 6: Categorizing and Tagging Words I

• Week 7: Categorizing and Tagging Words II

• Week 8: Midterm Exam (4/21)

• Week 9: Extracting Information from Text I

• Week 10: Extracting Information from Text II

• Week 11: Analyzing Sentence Structure I

• Week 12: Analyzing Sentence Structure II

• Week 13: Building Feature-Based Grammars

• Week 14: Analyzing the Meaning of Sentences

• Week 15: Managing Linguistic Data

• Week 16: Final Exam (6/16)

Memo

By default, the classes on Thursday will be offered in the classroom and the classes on Tuesday will be offered on-line. As such, the first class will be offered online. However, the subsequent classes may be offered on-line, depending on how Covid-19 situation improves substantially. Currently, we plan to conduct the midterm and final exams in the classroom, but they may also be substituted into several affordable homeworks if it is not feasible to conduct such exams in the classroom. The class size will be increased by up to 50% at the start of the add/drop period. If the first class cannot be offered in the classroom due to the situation on that day (3/3), the zoom address will be given both in the KLMS course site and here as well.