Skip to main content

Course Description

Introduction to the main approaches, tools, and methods related to computational modeling and learning of morphology and morphophonology.

This course will examine these major questions: * How do we model our linguistic knowledge in morphology and morphophonology computationally? * Are such models something we could learn automatically from either raw data or annotated data? * What do our computational models tell us about the nature of morphology?

The course has both a practical and a theoretical component. On the practical side, we want to explore current methods to model morphology computationally and what kinds of applications can be derived from such models. Many natural language processing systems rely on a morphophonological component at some stage, reflecting the importance of adequate and accurate treatment of this part. The goal is to achieve fluency in translating linguistic generalizations into a working computational model.

From a more theoretical perspective, computational morphology and morphophonology studies the computational properties of sound and word-formation patterns. Investigating these properties formally helps distinguish actually occurring patterns from logically possible patterns. Computational models are both accurate and explicit at the same time and thus allow for deeper insight into the nature of phonological and morphological processing from a cognitive perspective. Computational analyses also contribute to the ongoing discussion on the requisite formal power of theoretical models of word-internal patterns in linguistics.

Computational morphology and phonology are also very active current research topics. An aim of the course is to familiarize ourselves with contemporary questions and research results. The main topics to be discussed are: * Modeling phonology and morphology – Formal analysis – Finite-state implementations of generative models – Applications of morphophonological models * Learning – Formal analyses of learnability – Supervised and semi-supervised learning – Unsupervised learning


Lane Schwartz - Office hours Tue 5:00-6:00 PM in Foreign Languages Building, room 4019, and by appointment

Time and place

Tuesdays and Thursdays 2:00-3:20 PM, 1203 1/2 W. Nevada Street, Computer Lab

Required Texts and Tools

Schedule and Readings

Students are expected to regularly review the schedule of assigned readings and video lectures. This schedule is subject to change.

Learning Goals & Outcomes

Students are expected to attend class, attentively read assigned readings, attentively view assigned video lectures, regularly practice the presented tools and techniques, and complete all assigned work.

Students who do so are expected to attain the learning goals and outcomes.


Students will be assessed on the extent to which they have attained the learning goals & outcomes. This assessment will be primarily hands-on, assessed through a combination of daily quizzes, practical exercises, homework assignments, and projects.

Grades will be assessed on a 10-point fixed letter grade system.

Academic Integrity

This course follows the University of Illinois Student Code regarding Academic Integrity. The College of Liberal Arts and Sciences also has an excellent web page on the topic. You are expected to read these resources prior to the second day of class, and to understand your responsibilities with regard to Academic Integrity.

All work submitted for this class must be solely your own. Violations of Academic Integrity include, but are not limited to, copying, cheating, and unapproved collaboration. Violations will not be tolerated.

Absences and Late Work Policy

Students are expected complete all assigned readings and video lectures prior to the class for which they are assigned.

If a student will be absent from class for any reason, the student is expected to inform the course instructor by email ahead of time. Daily participation and quiz credit for excused absences may, at the discretion of the instructor, be made up by means of additional assignments.

If a student has a disability or condition that requires special consideration, the student is expected to present the requisite letter from the University Division of Disability Resources and Educational Services no later than the beginning of the second day of class.

Homework assignments are expected to be turned in on time. Homework turned in late will be docked 5 percentage points per day late (this corresponds approximately to half of a letter grade per day late). However, it is understood that illness and other extraordinary events do occur from time to time. In order to accommodate such extraordinary events, students will be allotted a budget of 3 penalty-free late days for which no late penalty will be assessed. Penalty-free late days are intended to accommodate unforeseeable extraordinary events, not poor planning or poor time management.

If a student wishes to make use of a penalty-free late day, the student must do all of the following prior to the current assignment deadline:

  • Send an email addressed to both the instructor and the TA. The email must have the exact subject heading "Penalty-free late day". In the body of the email, the student must explicitly request the use of a penalty-free late day.
  • In the student's git repository for the assignment, the student must note the request in the appropriate file, check in the change, and push the change to the appropriate remote repository.
Only when all of these steps have been taken prior to the deadline will a penalty-free late day be applied. If a student wishes to make use of more than one penalty-free late day per assignment, all of the above steps must be performed separately for each penalty-free late day.

Penalty-free late days may not be used to extend any deadline beyond the last regular day of class for the semester.

For some or all homework assignments, the correct solution will be presented to the class after the homework deadline. Under no circumstances will late work be accepted after the solution has been presented to the class.