January 19, 2018

Syllabus: LING2001, Spring 2018 (Yip)

Course: Computational Linguistics

Day/Time: Friday, 12:30–2:20
Location: CPD-LG.62
Prerequisite: LING1000
Instructor
Name: Dr. Jonathan Yip
Email address: yipjonat@hku.hk
Office location: 906 Run Run Shaw Tower

Description:
Computational linguistics is an interdisciplinary field of study drawing both on linguistics and
computer science. Computational linguistics research thus involves some knowledge of both
fields. The goal of this course is to provide a thorough introduction to the basic methods and
issues in computational linguistics for students with some background in linguistics, but none
in programming and computer science. The focus will be on hands-on experience learning,
using a human-level programing language, Python. Students with no prior computational
programming experience will be introduced to basic computational techniques for language
data analysis and linguistic research. They are expected to acquire basic skills in using a
programming language for practical applications such as data mining, searching corpora, text
analysis, and modeling linguistic processes mainly in phonology, morphology, and syntax.

Course Texts (optional):

Jurafsky, Daniel & Martin, James (2008) Speech and Language Processing: An Introduction
to Natural Language Processing, Computational Linguistics, and Speech Recognition,
Second Edition.

Downey, Allen (2012) Think Python: How to Think Like a Computer Scientist, Cam-
bridge University Press. Available free from: http://greenteapress.com/wp/
think-python/

Course Requirements:

1. Class Participation 15%

2. Homework Assignments 45%
3. Take-home Midterm 20%
4. Take-home Final exam 20%

LING2001: Yip Spring 2018

 January 19, 2018
Homework Information:
Homework sheets will be available for download on Moodle. Completed homeworks are to
be uploaded to the course website. Unless otherwise indicated on the assignment, hardcopy
assignments will not be accepted. I strongly prefer PDF and RTF to licensed file formats
(please don’t give me Word files).

Late Homework Policy:

I will accept late homework if you ask in advance for an extension. “In advance” means
more than 24 hours before the assignment is due. However, homework submitted late may
be subject to a substantial grade reduction.

Honor Policy:
Appropriating someone else’s work and portraying it as your own is cheating. Collaborating
with someone and portraying that work as solely your own is cheating. Obtaining answers
to homework assignments or exams from previous semesters is cheating. Falsifying data or
experimental results is cheating. (Please take some time to review the information provided
at the following website:
http://www.rss.hku.hk/plagiarism/page2s.htm.) If you are caught cheating, you may
receive a failing grade and/or face appropriate disciplinary actions. Some general guidelines
are:
1. Do not seek solutions to homework problems or exams from outside sources, including
books (other than the textbook) or the Internet.
2. Do not copy other students’ homework assignments. To minimize this temptation,
always type up your homework answers by yourself, separately from your study group
or other students in the class.
3. Once your have started to work on your midterm or final exam, do not discuss it with
other students, until after you have turned it in and the exam time is over.
4. Do not falsify data or other results in your homeworks.
5. Cite all sources used and cite and designate all quotations as such.

Study Groups:
I encourage students to form study groups to talk about readings and lectures, and especially
to discuss and work through understanding how to solve homework problems. Invite me if
you want and I’ll try to come. However, after you figure/argue them out together, you must
do the work and type up your homework answers entirely on your own, separately from the
other study group members. You must also list the names of all members of your group at the
top of your assignment. Failure to list study group members is an unethical misappropriation
of others’ contributions without acknowledgement.

LING2001: Yip Spring 2018

 January 19, 2018

Week Topic Assignments

Jan. 19th
1 What is Computational Linguistics? Readings: JM Ch. 1
Jan. 26th*
2 Regular Expressions, FSA Readings: JM Ch. 2;
Lab: Getting started with Python Worksheet 1 assigned
Feb. 2nd
3 Readings: JM Ch. 3;
Morphology & Finite State Transducers
Worksheet 1 due
Feb. 9th*
4 N-Grams Readings: JM Ch. 4;
Lab: TBD Worksheet 2 assigned
5 Feb. 16th: No class (Lunar New Year)
Feb. 23rd
6 Readings: JM Ch. 5;
Part of Speech Tagging
Worksheet 2 due
Mar. 2nd*
7
Parsing Readings: JM Ch. 13;
Lab: TBD Take-home Midterm assigned
8 Mar. 9th: No class (Reading Week)

9 Mar. 16th: No class (HKU Foundation Day)

Mar. 23rd
10 Statistical Parsing Readings: JM Ch. 14
11 Mar. 30th: No class (Good Friday)
Apr. 6th*
12 Complexity Readings: JM Ch. 15;
Lab: TBD Worksheet 3 assigned
Apr. 13th
13 Readings: JM Ch. 16;
Unification
Worksheet 3 due
Apr. 20th
14 Computational Lexical Semantics Readings: JM Ch. 20
Apr. 27th
15 Readings: JM Ch. 21;
Discourse
Take-home Final assigned
* We will meet in the Lab (9.62 RST) on these days.

LING2001: Yip Spring 2018