LING 5801: Introduction to computational linguistics (CL1)
Autumn 2017
Tuesday-Thursday 9:35-10:55
Scott Lab E 105
Marie-Catherine de Marneffe
Office hours: Thursday 1:30-2:30 or by appointment
Ohio Stadium East, room 118E
Description
This course provides an introduction to theory-driven computational linguistics for graduates and advanced undergraduates, focusing on morphology, syntax and lexical semantics. The course includes some formal background and emphasizes linking the theoretical discussions to practical experience implementing algorithms. The course is part of the two-course introduction to computational linguistics. The second half, LING 5802, focuses on data-intensive, statistical computational linguistics and is offered in Spring.
Prerequisites
LING 3802, LING 5000, CSE 3321, CSE 3521, CSE 5052, or permission of instructor. Not open to students with credit for LING 684.01.
Content topic list
- Regular languages: Regular expressions and Finite state automata
- Program correctness and complexity
- Morphology, syntax and lexical semantics
- Phrase-structure and dependency parsing
- Probability theory
- Unix skills and Python scripting
Network account
If you have a linguistics network account, you can use the linguistics computer lab in the stadium. The computers in this lab are installed with all software required for this course. If software does not appear to be working, you should contact Jim Harmon (Ohio Stadium East 108G) during normal working hours. If you don't have access to a computer, let me know, and we will set up a linguistics network account for you.Syllabus
The current page and the schedule page serve as the syllabus for this course.
Course requirements
There will be five assignments to turn in. Students will be encouraged to work collaboratively in small groups, but everyone has to turn in his/her own assignment.
Periodically there will be day to day short assignments strongly recommended, but that do not have to be turned in. Participation in class is mandatory.
When readings are assigned, students are expected to come to class ready to discuss the reading(s).
A tentative schedule for the semester is posted on the schedule page. Readings and assignments may change! Deadlines will be announced in class too.
Grading
This is a 3-credit course, graded on a letter-grade (A, B, C, D, E) basis. Students are expected to attend class meetings, complete reading and assignments, as well as actively participate in class discussions.
Homeworks (80%): Completing five assignments, some paper and pencil, some programming. Homework assignments are due by the beginning of class. No late assignments will be accepted. The lowest score of one homework will be dropped if and only if *all* homeworks are turned in on time.
Participation (20%): Regular attendance in class as well as active participation is required.
Grades will be assigned using the standard OSU scale.Website and Carmen
Materials for each unit will be posted on the website, as will the slides presented in class. Datasets and readings which cannot be made publicly available will be on Carmen or on the Linguistics network.
Note that email from Carmen is sent to your official email address (Name.Number@osu.edu). You should read email sent to your official OSU account on a daily basis.
Make-up Policy
If you know you won't be able to make a deadline, please see me before you miss the deadline! Otherwise you will be penalized.
Policy on Academic Misconduct
As with any class at this university, students are required to follow the Ohio State Code of Student Conduct. In particular, note that students are not allowed to, among other things, submit plagiarized (copied but unacknowledged) work for credit. If any violation occurs, I am required to report the violation to the Council on Academic Misconduct. See the Committee on Academic Misconduct's Frequently Asked Questions.