UT Austin LIN 313: Language and Computers

Fall 2026

Course Information

Instructor: Prof. Kanishka Misra
Email: kmisra@utexas.edu
Meeting Times: Tuesday & Thursday 2:00pm - 3:30pm
Location: PAR 1 (Address: 208 W 21ST ST, AUSTIN, TX 78712; link)
Canvas: https://utexas.instructure.com/courses/1453816
Office Hours: Wednesdays, 4-5pm or by Appointment.
Office: RLP 4.428

This class will have a final. The dates haven’t been scheduled by the UT registrar yet, but they will be held either on Dec 10, 11, 12, or 14. Please do not plan to travel until after the last university final exam day.

Course Summary

In the past decades, the widening use of computers has had a profound influence on the way we communicate, search and store information. For the overwhelming majority of people and situations, the natural vehicle for such information is natural language. Whenever you use spellcheck or Grammarly, talk to Siri, do a Google search, interact with a robot voice on the phone, or are fed targeted ads, you are interacting with natural language technology. Remarkably, even the language technology of 5 years ago is now far out of date, when you consider modern models like ChatGPT/Claude/Gemini that process language in amazing ways. A major reason for this is the machine learning and big data revolutions, which have together made it possible for machines to learn using huge amounts of data.

This course uses natural language systems like large language models (LLMs) to motivate students to exercise and develop a range of basic skills in formal and computational analysis. The course philosophy is to understand concepts that led to the rise of LLMs, and ground them in real world examples. We introduce strings, tokenization, vector-based representations, as well as a range of algorithms defined over these structures and techniques for probing and evaluating systems that rely on these algorithms. The course goes beyond merely subjective evaluation of systems, emphasizing analysis and reasoning to draw and argue for valid conclusions about the design, capabilities and behavior of natural language systems.

Evaluation will be based on homeworks, midterm, final, and a conversation with the instructor during office hours (x2).

Learning Outcomes

1. You will be able to explain what kinds of problems have to be solved in order for computers to do useful things with language. In order to train a computer to perform a human language task, we first have to understand something about how human language works and what kinds of problems need to be solved.

2. You will learn how to approach tasks from a computational perspective. This is NOT a programming class, but through class exercises and homework, you will gain experience thinking like a computer scientist and about how a computer scientist would go about solving problems in human language.

3. You will gain insight into the technology that underlies a wide variety of human language technologies, especially LLMs: from basic tokenization to vector-based representations to text classification to sequence modeling to modern day LLMs.

4. You will gain a better understanding of the challenges around work in computational linguistics, as well as an overview of how computational models are evaluated.

Note: Some material will draw on computational or statistical expertise to fully understand and may be difficult. We don’t expect you to have that expertise. So don’t be daunted: part of the point of this course is to talk through and get more familiar with these ideas and techniques.

Readings

There are no required textbooks for the class, but there are occasional readings/videos, which are posted in the “Before Class” part of the schedule (as shown below). Three of these do draw from existing textbooks:

• Caroline Rowland. (2013). Understanding child language acquisition. Routledge. (specific chapter posted on Canvas, though the full book is available through UT Libraries.)
• Glass, L., Dickinson, M., Brew, C., & Meurers, D. (2024). Language and computers. BoD–Books on Demand. Free PDF at: https://langsci-press.org/catalog/book/454 (click on PDF on the right panel).
• Daniel Jurafsky, & James H. Martin (2026). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models. https://web.stanford.edu/~jurafsky/slp3/

All readings listed in the schedule are accessible online to UT students registered in the course. As shorthand, the Glass et al. (2024) and Jurafsky and Martin (2026) books are referred to as GDBM and SLP, respectively.

Course Schedule

Wk	Date	Topic	Homeworks	Before class
1	Aug-25 (Tu)	Introduction to the course		Course Survey
1	Aug-27 (Th)	Communication Game Demo (In class)	Not a HW but do the course survey!
2	Sep-01 (Tu)	Structure of Language 1	HW 1 released.	Read Rowland (2013). Ch 1 Pages 2 to 13 (before sec. 1.4)
2	Sep-03 (Th)	Structure of Language 2
3	Sep-08 (Tu)	Encoding Language + Probability (if time permits)		GDBM Ch. 1
3	Sep-10 (Th)	Probability continued	HW 1 Due. HW 2 released.
4	Sep-15 (Tu)	Language and Information (w/ Wordle)		Watch a Ted talk (in more ways than one) Wordle Demo!
4	Sep-17 (Th)	Language and Information (w/o Wordle)
5	Sep-22 (Tu)	Language Modeling and Ngrams I		SLP Ch. 3 (pp. 1-10) Note: it gets a bit technical after p. 10 but feel free to read it!
5	Sep-24 (Th)	Language Modeling and Ngrams II
6	Sep-29 (Tu)	Tokenization		See SLP 3 Ch. 2 (pp 10-14) for BPE
6	Oct-01 (Th)	Intro to classification - Naive Bayes (not on mid term)	HW 2 Due.	StatQuest’s Naive Bayes (youtube) GDBM Ch. 5
7	Oct-06 (Tu)	Review 1
7	Oct-08 (Th)	Review 2 / Ask me anything / Cool research paper
8	Oct-13 (Tu)	Mid term		Topics: Structure of Language, Probability, Info theory n-grams, tokenization
8	Oct-15 (Th)	Classification/ML - Other algos (perceptron)	HW 3 released	GDBM Ch. 5
9	Oct-20 (Tu)	Evaluating Classification		GDBM Ch. 5
9	Oct-22 (Th)	Neural Networks		3B1B’s What is a Neural network? (youtube) 3B1B’s Gradient Descent (youtube)
10	Oct-27 (Tu)	Vectors 1		SLP Ch. 5 (pp. 1-10)
10	Oct-29 (Th)	Vectors 2		Jay Alammar’s Illustrated word2vec (blog) Optional: SLP Ch. 5 (pp. 10-27). This gets a bit technical, don’t get bogged down by details.
11	Nov-03 (Tu)	Neural LMs 1
11	Nov-05 (Th)	Neural LMs 2	HW 3 due HW 4 released
12	Nov-10 (Tu)	Psycholinguistics		Minicons Demo
12	Nov-12 (Th)	Inching close to modern LLMs: RLHF
13	Nov-17 (Tu)	Mixed Bag of Topics
13	Nov-19 (Th)	Multilingual/Speech and Sign	HW 4 due	Arnett and Chang’s Multilingual LM survey
14	Nov-24 (Tu)	NO CLASS - Thanksgiving!
14	Nov-26 (Th)	NO CLASS - Thanksgiving!
15	Dec-01 (Tu)	Review 1
15	Dec-03 (Th)	Review 2 / Ask me anything / Cool research paper
16	Dec-10/11/12/14	Final (UT hasn’t scheduled yet)		Topics: Everything!!! (before thanksgiving)

Grading

All homeworks are due end of day Thursday.

Category	Component	Weight	When	Where/Format
Homeworks (50%)	HW 1	10%	Due Sep-10 (Th)	Submitted on Canvas
	HW 2	15%	Due Oct-01 (Th)	Submitted on Canvas
	HW 3	15%	Due Nov-05 (Th)	Submitted on Canvas
	HW 4	10%	Due Nov-19 (Th)	Submitted on Canvas
Exams (40%)	Midterm	20%	Oct-13 (Tu)	In person, in class
	Final	20%	Dec-10/11/12/14 (TBD by UT)	In person
Office hour chit-chat (10%) (starts week 2)	Chit (visit 1)	5%	Sign up on Canvas	15 min 1:1 in office hours
	Chat (visit 2)	5%	Sign up on Canvas	15 min 1:1 in office hours

Grade Determination

Grade	Percentage
A	>= 93%
A-	>= 90%
B+	>= 87%
B	>= 83%
B-	>= 80%
C+	>= 77%
C	>= 73%
C-	>= 70%
D+	>= 67%
D	>= 63%
D-	>= 60%
F	< 60%

Attendance is not used as part of determining the grade.

Extension Policy

• Slip days: You will have a total of 6 free slip days that you can use throughout the semester. These apply to the homeworks only, and not to the exams or the office hour chit-chats. You can choose how many days you want to use, and however you want to distribute them; e.g., you can use one slip day per homework, or all 6 days for one homework and none for the others. Slip days cannot be used fractionally: submitting a homework 1 hour late incurs 1 slip day, 25 hours late incurs 2 slip days, etc. The slip days do count over breaks. So for HW 4, we will count the thanksgiving break as well.
• Extension permissions: Beyond the slip days, extensions may be granted on a case-by-case basis due to medical emergency or other circumstances that are extraordinary or emergencies in nature. You must reach out to the instructor to obtain an extension before the deadline in question.
• Late penalty: Once your slip days are used up, and if you did not obtain a permission for an extension, each day of lateness costs 10%: if you are X days late in submitting a homework (after slip days have been used up), the maximum possible you can score is (100 - X*10)% of the original homework points. For example, a homework submitted 2 days late (after all slip days have been used up) can score at most 80%. A homework submitted 10 or more days late can no longer earn credit.

What in the world is Office hour chit-chat?

Great question! I’d love to do two 1:1 meetings with each of you during the semester. The goal of this meeting would be for you to come to my office hours, and do any of the following for 15 mins (not more):

• Describe to me a concept discussed in class that you really appreciated/enjoyed (or didn’t). You don’t have to give me a 1 hr 15 min lecture on it, but just pick a topic, and have a conversation with me. Tell me what you liked (or didn’t like) about it.
• Walk me through a homework problem on the whiteboard / on a piece of paper (you’d have to bring the piece of paper though, I will obviously supply the whiteboard), describe to me all the steps you’re taking to solve it.
• If you got an LLM-powered system (ChatGPT/Claude/Gemini) to explain a class concept to you (see AI policy below) and found it cool and of great value, share what you liked about it. I am sure there’s tons to be learned from LLMs (despite their clear problems), and I am all ears to know how you’ve been using them creatively.

The chit-chat is not an oral exam – your goal is not to be right, you just have to be able to talk about something we discussed in the class. Why are we doing this then? It will tell me something about the progress you’ve made, and if I need to do anything to change the way I teach! And also, it might build confidence in you – you get to practice explaining a problem or a concept to someone, which could especially be useful during job interviews!

To make sure everyone gets a chance, I will have sign up sheets posted on canvas soon. The chit-chat will start during the second week. For those who have a clash with the office hour timings, please email me to book a separate meeting.

University Policies

Academic Integrity

Each student in the course is expected to abide by the University of Texas Honor Code: “As a student of The University of Texas at Austin, I shall abide by the core values of the University and uphold academic integrity.” Plagiarism is taken very seriously at UT. Therefore, if you use words or ideas that are not your own (or that you have used in a previous class), you must cite your sources. Otherwise you will be guilty of plagiarism and subject to academic disciplinary action, including failure of the course. You are responsible for understanding UT’s Academic Honesty and the University Honor Code which can be found at: https://deanofstudents.utexas.edu/conduct/standardsofconduct.php

Academic Dishonesty Policy

You are encouraged to discuss assignments with classmates. But all written work must be your own. Students caught cheating will automatically fail the course. If in doubt, ask the instructor.

Course AI Policy

We encourage you to use ChatGPT/Claude/Gemini and other related tools to understand concepts in this class. Understanding the capabilities of these systems and their boundaries is a major focus of this class, and there’s no better way to do that than by using them! However, using these models to solve the problem by simply giving them the question and getting them to write the answers for you is not useful (well it is if your goal is to save time and learn nothing, but hopefully you want to learn stuff in this course!) and prohibited.

An example of a good question is: “I want to understand how cosine similarity works, can you come up with an example and show me” –> and then use what you learn from this by attempting to solve the problem yourself.

An even more creative example is: “I want to understand X. Can you build a webapp that can explain X by demonstration” (Hint: Many of the demos I made for this class would not have been possible without Claude, even though they were completely my idea.)

Sharing of Course Materials is Prohibited

No materials used in this class, including, but not limited to, lecture hand-outs, videos, assessments (quizzes, exams, papers, projects, homework assignments), in-class materials, review sheets, and additional problem sets, may be shared online or with anyone outside of the class unless you have my explicit, written permission. Unauthorized sharing of materials promotes cheating. It is a violation of the University’s Student Honor Code and an act of academic dishonesty. I am well aware of the sites used for sharing materials, and any materials found online that are associated with you, or any suspected unauthorized sharing of materials, will be reported to Student Conduct and Academic Integrity in the Office of the Dean of Students. These reports can result in sanctions, including failure in the course.

Notice about missed work due to religious holy days

A student who misses an examination, work assignment, or other project due to the observance of a religious holy day will be given an opportunity to complete the work missed within a reasonable time after the absence, provided that he or she has properly notified the instructor. It is the policy of the University of Texas at Austin that the student must notify the instructor at least fourteen days prior to the classes scheduled on dates he or she will be absent to observe a religious holy day. For religious holy days that fall within the first two weeks of the semester, the notice should be given on the first day of the semester. The student will not be penalized for these excused absences, but the instructor may appropriately respond if the student fails to complete satisfactorily the missed assignment or examination within a reasonable time after the excused absence.

Policy on Class Recordings

HOP 2-9970 prohibits students from recording class instruction (audio or video) unless a student obtains the instructor’s permission or Disability & Access has approved audio recording as an accommodation.

Here’s what it states:

Audio or visual recording devices may not be used in University classrooms or laboratories unless specifically approved by the instructor or Disability and Access. Instructors may create electronic recordings of their classes and have the discretion to allow or disallow students or visitors to make electronic recordings of their classes. Any recording(s) must be limited to legitimate educational purposes and may not be shared with or distributed to others in any form unless otherwise permitted by HOP 9-1610, Student Rights Under the Family Educational Rights and Privacy Act (FERPA). If an instructor permits a student to electronically record their class, the recording(s) must be used solely for the educational use of the student or other students in that section and year of the class. Individuals who violate these limitations may be subject to disciplinary proceedings. An instructor must allow a student to electronically record their class if the student has received an accommodation through Disability and Access that permits the student to electronically record class.

Student Support Services

Disability and Access

The university is committed to creating an accessible and inclusive learning environment consistent with university policy and federal and state law. Please let me know if you experience any barriers to learning so I can work with you to ensure you have equal opportunity to participate fully in this course. If you are a student with a disability, or think you may have a disability, and need accommodations please contact Disability and Access (D&A). Please refer to D&A’s website for contact and more information: https://disability.utexas.edu/ (phone: 512-471-6259, email: access@austin.utexas.edu). If you are already registered with D&A, please deliver your Accommodation Letter to me as early as possible in the semester so we can discuss your approved accommodations and needs in this course.

Counseling and Mental Health Center

The Counseling and Mental Health Center serves UT’s diverse campus community by providing high quality, innovative and culturally informed mental health programs and services that enhance and support students’ well-being, academic and life goals. To learn more about your counseling and mental health options, call CMHC at 512-471-3515.

If you are experiencing a mental health crisis, call the CMHC Crisis Line 24/7 at 512-471-2255.

The Sanger Learning Center

Did you know that more than one-fifth of UT undergraduate students use the Sanger Learning Center each year to improve their academic performance? All students are welcome to take advantage of Sanger Center’s classes and workshops, private learning specialist appointments, peer academic coaching, and tutoring for more than 160 courses. For more information, please visit https://undergraduates.utexas.edu/ or call 512-471-3614 (JES A332).