Syllabus for Word Meaning and Concepts: LIN386M
Instructor Contact Information
To get an account on the computational linguistics lab machines, please send me an email.
You can then log in remotely to iliad.ling.utexas.edu or odyssey.ling.utexas.edu.
Syllabus and Text
This page serves as the syllabus for this course.
There is no course textbook. Readings will be from texts that are announced on the schedule page. These readings will either be freely available online, or they will be available online at the UT library, or they will be made available for copying.
Exams and Assignments
As this is a seminar, there will be no midterm or final exams for this class. For due dates of project papers, and more information about reading presentations, please see the assignments page. A tentative schedule for the entire semester is posted on the schedule page. Readings and exercises may change up one week in advance of their due dates.
Philosophy and Goal
Word meanings are hard to characterize. There are cases in which word meanings are systematically related and can be derived systematically, in particular through metonymy. But beyond metonymy, dictionaries do not even agree on how many senses different words have.
There has been work on characterizing word meaning in different areas: lexicography, theoretical linguistics, cognitive linguistics, philosophy of language, psychology, computational linguistics, and artificial intelligence.
The goal of this seminar is to compare and contrast approaches of word mening characterization from these different areas, asking how each area might benefit from the other areas' viewpoint.
Some of the questions discussed will be:
In what ways can word senses be related, systematically or otherwise?
Is it reasonable to assume that each word has a true number of senses that can be detected?
What is the relation between word meaning and human concept representation?
Can word meaning be represented through prototype representations?
How are the senses of polysemous words represented in the mind, and what can we learn from this about polysemy in general?
To what extent can word meaning be decomposed into features?
What facets of word meaning can be represented through geometric models?
In representing word meaning, do we need to look beyond individual words to events and argument structure?
Note that this is not a computational seminar, though we will include computational approaches. The main part of the grade will be determined through a course project, which may be theoretical, a corpus study, or a computational study.
This course provides an in-depth discussion of different models of word meaning.
Relations between word senses: We will discuss accounts of regular polysemy, and approaches in psychology that study relations between senses in the human mind.
Current theories of human concept representation: We will look at prototype, exemplar, and knowledge-based theories. We will also discuss how concept representation theories relate to word meaning.
Aristotelic concepts and concepts with “fuzzy boundaries”: An old debate on whether concepts can be prototypes yields insights on the representation of composite concepts.
Computational approaches to representing word meaning: We study several computational approaches to representing word meaning, asking what linguistic or cognitive insights they model and what they predict about the nature of word meaning
Structured representations of word meaning: representing and making use of argument structure
Representing word meaning through features
Reading presentation (30%): You will give a 20 minute presentation on one of the papers listed in the readings for the class, and lead the subsequent discussion about the paper.
Project proposal draft (15%): After about one third of the semester, you will propose a topic for your final project. You are encouraged to discuss this with the instructor in advance. The proposal will be in written form and should be roughly 2-3 single-spaced pages. The draft will be evaluated primarily on written expression, coherence of argument, and significance and difficulty of the project. The proposal should include at least 4 references. Feedback will be given both on writing and content.
Project progress report (15%): The progress report should be a revision of the proposal, and in addition contain information on progress to date. It should take into account comments given on the proposal. Expect it to require significant rewriting, as opposed to just editing the proposal. The progress report will be graded primarily on written expression and coherence of argument. Feedback will be given on both writing and content.
Project final report (40%): The final report builds on the progress report and presents the project results and conclusions. It should be 4-8 pages in length, and include at least 8 references. The grade will be based on the written report.
If you turn in your assignment late, expect points to be deducted. Extensions will be considered on a case-by-case basis, but in most cases they will not be granted.
By default, 5 points (out of 100) will be deducted for lateness, plus an additional 1 point for every 24-hour period beyond 2 that the assignment is late. For example, an assignment due at 11am on Tuesday will have 5 points deducted if it is turned in late but before 11am on Thursday. It will have 6 points deducted if it is turned in by 11am Friday, etc.
The greater the advance notice of a need for an extension, the greater the likelihood of leniency.
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.
Notice about students with disabilities
The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. To determine if you qualify, please contact the Dean of Students at 471-6529; 471-4641 TTY. If they certify your needs, we will work with you to make appropriate arrangements.
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.