LAC: Language and The Computer

Francis Bond: 2010, 2011, 2012, 2013, 2015, 2017, 2021, 2023, 2024s, 2024w.
Michael Wayne Goodman: 2019, 2020.

Traditionally linguistic analysis was done largely by hand, but computer-based methods and tools are becoming increasingly widely used in contemporary research. This course provides an introduction to skills and resources that can assist the linguist, or indeed anyone, in performing fast, flexible, and accurate quantitative analyses. Students will learn a programming language (Python) along with techniques for processing human language data. No previous programming experience is required: we will teach you the basics of programming and computational linguistics along with some good software engineering practices.

This year we are doing a major overhaul, with a new text book! Please forgive any rough edges.

Course page (here); Source on Github

Thursday 15:00-16:30, Room 2.39, tř. Svobody 26, 779 00 Olomouc

Course Outline

Week: Date	Content	Data Structures	Readings	Projects
1: 09-26	Why do NLP? Why Python? Setting up Colab and some simple data-types	string	PCC 1 & 2, 📝 Cheat Sheet, 📝 Cheat Sheet BW
2: 10-03	Introducing and Working with Lists	list, tuple	PCC 3 & 4, 📝 list, 📝 list BW DiP3 2.4
3: 10-10	If Statements	boolean	PCC 5, 📝 if/while, 📝 if/while BW
4: 10-17	Dictionaries, User Input and While Loops	dictionary, set	PCC 6 & 7, 📝 dict., 📝 dict. BW
5: 10-24	Functions		PCC 8, 📝 functions, 📝 functions BW
6: 10-31	Files and Exceptions		PCC 10, 📝 files/exceptions, 📝 files/exceptions BW	Project 1
Reading Week
7: 11-14	Testing Your Code		PCC 11,📝 testing, 📝 testing BW
8: 11-21	Regular Expressions	regex	Interactive RE, Wikiversity Python Programming/RegEx
9 11-28	Tokenization	No lecture
10: 12-05	Wordnet			Project 1 due Dec 06 24:00 CET
11: 12-12	Plotting
12: ---	Feedback, Review/catch up		Handy Summary of Python and NLP Concepts
13: 12-18 Wed!	Final In-Class On-Line Open-Book Programming Challenge		15:00–19:00, room 3.28 later for one student	Project 2 due Jan 31 24:00

Textbooks and Tools

Eric Matthes (2023) Python Crash Course, 3rd Edition (PCC) A Hands-On, Project-Based Introduction to Programming, No Starch Press, ISBN: 9781718502703
- It also comes with a set of handy references (📝: Cheat Sheets)
Other Python Books:
- Stephen Bird, Ewan Klein, Edward Loper (2009) Natural Language Processing with Python, O'Reilly.
  (Updated for Python3.0, 2019)
- NLTK Natural Language Toolkit
- Allen Downey (2016) Think Python: How to Think Like a Computer Scientist, O'Reilly
- Goldwasser and Letscher (2008) Object-Oriented Programming in Python, Prentice Hall David Lukeš, Rudolf Rosa (2020) An Introduction to Python for Linguists Visegrad Fund
- David Mertz (2003) Text Processing in Python, Addison-Wesley.
- Rowan Nichols (2024) Python (Nice online summary)
- Mark Pilgrim (2009) Dive into Python 3 (DiP3), Apress
- Al Sweigart (2019) Automate the Boring Stuff with Python, 2nd Edition, No Starch Press
- Even more: 5 Free Books to Help You Master Python
On-line environments and tutorials
- Python Warmups
NLP/Computational Linguistics
- Daniel Jurafsky and James H. Martin (2009) Speech and Language Processing, 2nd edition, Prentice Hall.
- Chris Manning and Hinrich Schütze (1999) Foundations of Statistical Natural Language Processing, MIT Press. Cambridge, MA.
Recommended text editors
- Notepad++ (MS Windows)
- Text Wrangler (Mac)
- Emacs (Everywhere)
Linguistic Style Guides
- (Computational) Linguistic Style Guidelines: a guide for the flummoxed.

Assessment and Solutions to Problems

Evaluation Criteria (same for all projects)

Code/Approach (50%)
- Does the program produce useful results
- Is it properly documented
  - comments
  - doc strings
- Does it use appropriate data structures?
Write Up (50%)
- Is it clear what was done and why?
- Does it adequately cite resources used?
- Does it adequately cite the linguistics literature?
- Does it include some evaluation?
- Is there any analysis of errors?
- Does it point out any remaining issues?
- Is it formatted correctly?

Assessment problems are generally open ended --- it is not expected that the student can solve them fully: the goal is to see how they approach the problem and understand it.

A note on using AI (such as ChaGPT or Claude)

Research shows (Shein 2024) that using AI to help code allows you to solve problems faster, but not to remember how to do it. The goal of this course is to learn the foundations of programming, you will retain them better if you solve the problems on your own.

Once you know more about how to program, you can and should use AI to help you. I do, and it is helpful, but it makes mistakes that a human wouldn't (or shouldn't). For example, I asked it to split data into 10 roughly equal bins, which it did, but it only returned nine of them! I noticed, because I could check the code and understand the output, ... That is what this course will teach you.

Course materials were originally heavily inspired by clt231: Introduction to Natural Language Processing at the University of Helsinki. Thanks to Graham Wilcock for letting us use them.

I will try not to make things too hard (cartoon from Abtruse Goose)

Instead this class should be like this (cartoon from XKCD)

Francis Bond <bond@ieee.org> <francis.bond@upol.cz>
Home page