Computational Linguistics 1

CMSC/LING 723; LBSC 774

Fall 2011

Class time: Tue/Thu 2:00 - 3:15pm    1 Sept - 19 Dec, 2011

Class location: CSI 2107

Instructor: Kristy Hollingshead Seitz
Email: moc.liamg@kgnilloh
Office hours: AVW 3155, for one hour after class and by appointment

TA: Aleksandrs Ecins
Email: ude.dmu.sc@snicea
Office hours: AVW 4470 3444 Tue/Thu 1:00 - 2:00pm

Homework submission email: moc.liamg@1102llaf.327gnilpmoc

Course mailing list webpage: groups.google.com/group/umd-cmsc723-fall-2011 (umd-cmsc723-fall-2011@googlegroups.com)

Items of note will be posted in this section.

11/14: HW5's deadline has been extended to Nov 17, with an option to receive extra credit if turned in on the original deadline of Nov 15.

11/4: HW5 is now available and is due Nov 15.

10/27: HW4 is now available.

10/25: HW4 will be due Nov 3.

10/18: Class will be cancelled next Thursday, Oct 27.

10/11: The midterm will now be given as a take-home midterm, handed out on Tuesday Oct 18, due back the next Tuesday, Oct 25.

9/29: HW3 is now available and is due Oct 13.

9/22: HW2 is now available and is due Sept 29.

9/9: HW1 is now available and now due on Sept 20.

9/1: HW0 is now available; Jimmy Lin's Python tutorial was added to the schedule page for today.

8/26: The course schedule is up!

8/20: First day of class is Thursday, September 1!

This is the first semester in our two-semester graduate sequence in computational linguistics. During this semester, we will focus on fundamental methods, algorithms, and data structures in natural language processing. Topics include: finite-state methods, context-free and extended context-free models of syntax; parsing and semantic interpretation; n-gram and Hidden Markov models, part-of-speech tagging; and natural language applications. Students completing this course will have a solid working knowledge of the basics of NLP and will be well prepared for the second semester course, which covers natural language processing with a focus on corpus-based statistical techniques.

This class fulfills the AI Area of the Computer Science MS Comps requirements.

Prerequisites: There will be a fair amount of programming required to complete the homeworks for this course, and therefore some programming experience is assumed. There is no official programming language for this course, but I strongly recommend using Python and the NLTK toolkit -- particularly if you are planning to continue on to Computational Linguistics 2 next semester -- unless you have a strong preference otherwise. You are expected to have a computer on which you can complete the homework assignments.

The textbook for the course is:
Jurafsky and Martin, Speech and Language Processing.

Approximately one third of the course readings will be conference papers and journal articles, which will be accessible online.

The purpose of grading, for this class, is to provide a quantitative measurement of your progress and understanding in the class, as well as a measurement of how well the class is doing as a whole.

50%	Exams
	25% each to midterm and final.
40%	Homeworks
	There are 8 homeworks of varying difficulty (and thus varying contribution to your grade). Homework is important in this class, and so exams (which are worth much more of your grade) will be designed such that completing and correcting your homeworks will help you perform well on the exams.
10%	Class Participation
	I really like an interactive class. Come to class, pay attention, do the readings, and contribute to class discussions!

Please note: the CS MS Comp grade (AI Area) will be based entirely on the average of the midterm and final exam grades.

Attendance

• Students who miss up to two classes for a medical reason must make a reasonable effort to contact me in advance, and bring a self-signed note upon return to class, acknowledging that the information provided is accurate. Subsequent absences will require medical documentation.
• Prolonged absences due to illness (multiple consecutive absences) require written documentation from a health care provider.
• Absence from either of the exams due to illness also requires documentation from a health care professional, as well as notifying me in advance when possible.
• If you know you will miss class due to religious observances, please notify me in advance, within the first two weeks of class.

Homeworks

• Homeworks must be completed individually.
• Plaigiarism will not be tolerated, and will result in a 0. However, discussing class concepts amongst your classmates is recommended and encouraged; generally, you can discuss concepts and pseudo-code, but do not share actual code. Please visit the Student Honor Council website for more information on the consequences of cheating, fabrication, facilitation, and plagiarism.

Late and Incomplete Work

• Assigments are due at the beginning of class, typically by e-mail to me and the TA unless otherwise noted.
• Homeworks that are late will still be graded if handed in within 48 hours of the deadline, but your score will automatically be halved. Exceptions can be discussed in the case of medical or family emergencies, but will only be considered prior to the homework deadline. After 48 hours, homeworks will no longer be accepted.
• I am unable to issue an 'Incomplete' grade. If an emergency arises, discuss with me as soon as possible and we will have to go to the department together.

Exams

• Exams will be in-class and open-book/open-note/open-laptop (but not open-internet).

Students with Disabilities

• The campus's Disability Support Service Office (DSS) works with students and faculty to address a variety of issues ranging from test anxiety to physical and psychological disabilities. To receive accommodations, students must first have their disabilities documented by DSS. The office then prepares an Accommodation Letter for course instructors regarding needed accommodations, which needs to be presented to me, the instructor, at the beginning of the semester (within the first three class sessions).

Class Cancellations

• Official closures and delays are announced on the campus website and the snow phone line (301-405-SNOW), as well as on local radio and TV stations. Information about possible rescheduling of course activities will be provided via e-mail and on this website once the campus has re-opened.
• If I am forced to cancel a class even though the University is open, due to inclement weather or illness, I will notify the class via e-mail (and on this website).

Page modified 11 October 2011.