Course Info for Ling773/CMSC773/INST728C, Spring 2013

Course Info for Ling773/CMSC773/INST728C, Spring 2013
Computational Linguistics II

Essentials

Location and time of the class:
Taliaferro Hall, Room 1103, Wednesdays 1:30-4pm.
Instructor:
Philip Resnik (resnik _AT_ umd.edu)
Office hours in AVW Williams 3133 or Marie Mount Hall 1401C, by appointment.
Office phone number: (301) 405-6760, though I check messages infrequently and e-mail is much more likely to get a timely response.
TA:
Wu Ke (wuke_AT_ cs.umd.edu) [note that Wu is Ke's surname]
Address for turning in assignments: ling773.sp2013@gmail.com.
Turn in assignments in PDF format, and include firstname.lastname in the file name.
Office hours: 2pm ~ 3pm Thursdays, at the CS Graduate Student Lounge (first floor of AVW)
Text:
Weekly readings listed in the schedule of topics, many from Christopher D. Manning and Hinrich Schuetze, Foundations of Statistical Natural Language Processing. This is not a required textbook in the official class description because it's possible to find it online (also here and see here for Ch5 and Ch9), though I think buying it is a great idea. Another useful book for background is Speech and Language Processing (Second Edition) by Dan Jurafsky and James Martin.
Syllabus:
See the schedule of topics.
Class announcements and discussion:
We will be using Piazza for announcements and online discussion. To sign up, go to https://piazza.com/umd/spring2013/ling773cmsc773inst728c/. Students are strongly encouraged to read and participate in class discussions and Q&A, and you're encouraged to post questions on Piazza rather than e-mailing the prof or TA. (Note that Piazza does let you do private postings to course staff if desired, though in general questions and answers are likely to be useful to everyone.) If you have any problems with the Piazza platform, or feedback for the Piazza developers, email team@piazza.com.
Also, in the past some students in this class have used del.icio.us to tag Web pages that are related to this course -- see http://del.icio.us/tag/cmsc773. Please feel free to contribute!

What's the course about?

This is the second semester in our graduate sequence in computational linguistics, and it will provide foundations for advanced seminars or research in computational linguistics. Computational linguistics has two main areas: how to built technology that does useful things with human language (this area is usually referred to as "natural language processing", NLP, or sometimes "human language technology"), and how to improve our scientific understanding of how language works using computational methods and models. Our main focus will be on NLP, but we will also be devoting some thought to how the models and methods we study can be useful when studying language from a scientific perspective.

The topics we'll cover are intended to get students up to speed on necessary background in order to understand and perform cutting-edge research in natural language processing, which requires a strong grounding in statistical NLP models and methods. Some of the topics are in the same areas as in Computational Linguistics I, but we will go deeper. As always, the syllabus is subject to revision; however, it will follow Manning and Schuetze's textbook relatively closely at least in early parts of the course.

As prerequisites, students are expected to be able to know how to program (your choice as to language), and will exercise this ability periodically in homework assignments and/or projects. Students are assumed to have taken the the first semester computational linguistics course or equivalent, and therefore the background knowledge required there is assumed here also: Unix for Poets, very basic prob/stats, and slightly less basic stats.

See the schedule of topics for class-by-class plans. In case of an emergency that closes the University for an extended period of time, see Piazza for announcements.

How will class be structured?

I tend to start each class with an opportunity for questions or discussion related to the previous class or assignment. Then it's typically a lecture format, although I strongly encourage interruptions for questions and I also pause for discussions; if the number of interruptions threatens to throw me off track, trust me, I'll make sure to keep things under control. Although there's no avoiding some detail work at the board in a course like this, I don't particularly like slogging through details at the front of a room -- I believe that detailed working-through is your job, either when you're doing the reading ahead of class (which you should make sure to do!), going through things afterwards (also a good idea!), or both. My job is to make sure you understand the ideas, and that you have what you need to work through those details and understand why you're doing it.

How will the course be graded?

Students will be evaluated on their ability to master the content of the material in the course and to think critically about ideas presented to them. That last part's important. My favorite kind of question on a homework or on an exam is one where you're asked to assess pros and cons or to apply something you've learned to a new situation.

	45%	Class assignments/projects These are graded on a high-pass (100%), low-pass (50%) or fail (0%) basis. Some of these are one-week assignments, and others might be a multi-week assignment or project; either way the amount of time given for the assignment is calibrated to the amount of work that should be involved and the amount of credit you'll get for the assignment; for example, a particular homework might be described as a two-week assignment, meaning that you'll have two weeks to do it and you'll receive two homeworks' worth of credit for it. Assignments may involve on-paper exercises (e.g. walking through algorithms or calculations), hands-on programming, or analysis of data. I am comfortable in principle with students working together on assignments in part or in whole, but if you wish to do so, please ask me in advance because there are certain conditions that I will impose.
	25%	Midterm exam This will be a take-home exam, and it will not involve programming.
	25%	Final exam This will be structured as a multi-week project that will definitely involve programming.
	5%	Class participation I care enough about participation to make it part of the grade. It may be a small part, but it's definitely been known to tip the balance from a B+ grade to an A-, so please don't neglect it. This is necessarily subjective, because I am judging both the quantity and quality of your participation, but the calibration is pretty straightforward. It's a 5-point scale, and if you regularly ask relevant questions, volunteer answers (even if they're wrong!), and help make the class discussion interesting, you'll get 5 out of 5 points. If you show up to class prepared and contribute to the conversation every couple of classes, you'll get 3 out of 5 points. If you are regularly sitting in class but participating rarely or not at all, you'll get 1 point for showing up. If you don't show up consistently, you'll get zero.
	EC	Extra credit There will probably be some extra credit offered, either within assignments or as extra assignments. I sometimes also offer extra credit for attending the Computational Linguistics Colloquium and turning in a one-page summary/discussion of the talk.

CS MS comps. Note that, per policy of the Computer Science Department, the CS MS comp grade (AI area) will be based entirely on the average of the midterm and final examinations.

Policy for Incomplete Work

Late assignments. If an assignment is late by up to 24 hours, the grade will be reduced by 20%. By 48 hours, 40%. After 48 hours, no credit. Potential exceptions include the one time Late Assignment Exception (see next bullet), urgent medical issues, family emergencies, or other valid reasons we can discuss if necessary. What's crucial is that if you do have a problem or issue, you talk to me about it as soon as possible.
I can tell you in advance that there are several common problems I will not consider as valid reasons for failing to get work in on time. These include (a) failure to manage your time properly, including being busy with another course, a piece of research, or a paper submission deadline; (b) discovering an assignment is harder than you expected it to be (see item a); and (c) losing code or data that should have been backed up, unless it's someone else's fault.
Late assignment exception. Each student can ask to extend an assignment due date by 48 hours once during the semester, no questions asked, as long as the request takes place before the assignment is due. (E-mailing the request at the time the assignment is due, in place of turning in the assignment, is ok. Make sure you cc yourself so you've got a timestamp on the request.) Note that if you are taking the Late Assignment Exception, you cannot extend the due date further with 20% or 40% penalty. If it's not turned in 48 hours after the original due date, it won't be accepted.
'Incomplete' as a grade. I will not issue an 'incomplete' as a course grade except for serious, valid reasons, generally in the category of serious emergencies. If you are having problems of any kind, please talk to me as soon as possible. In the event that a medical issue interferes with any class requirement, you are required to let me know in advance or as quickly as can reasonably be expected, and to provide documentation signed by a health care professional.

Other important notes

Academic integrity policy. The Honor Code and Honor Pledge prohibits students from cheating on exams, plagiarizing papers, submitting the same paper for credit in two courses without authorization, buying papers, submitting fraudulent documents, and forging signatures. On the midterm and final, you will be expected to write and sign the following pledge: I pledge on my honor that I have not given or received any unauthorized assistance on this examination (or assignment).

Cheating: What you represent as your own work must be your own work. However, talking with one another to understand the material better is strongly encouraged. Recognizing the distinction between cheating and cooperation is very important. If you simply copy someone else's solution, you are cheating. If you let someone else copy your solution, you are cheating. If someone dictates a solution to you, you are cheating. Everything you hand in must be in your own words, and based on your own understanding of the solution. If someone helps you understand the problem during a high-level discussion, you are not cheating. If you work collaboratively with explicit permission from the instructor, you are not cheating. We strongly encourage students to help one another understand the material presented in class, in the readings, and general issues relevant to the assignments. Any student who is caught cheating will be given an E in the course and referred to the University Student Behavior Committee. Please don't take that chance - if you're having trouble understanding the material, or if you need some help clarifying what is ok to do and what is not, please let us know and we will be more than happy to help.

Special needs. Any student eligible for and requesting reasonable academic accommodations due to a disability is requested to provide to the instructor a letter of accommodation from the Office of Disability Support Services (DSS) within the first two weeks of the semester. You may reach them at 301-314-7682 or by visiting Susquehanna Hall on the 4th Floor.

Philip Resnik, Professor
Department of Linguistics and Institute for Advanced Computer Studies


Department of Linguistics
1401 Marie Mount Hall            UMIACS phone: (301) 405-6760       
University of Maryland           Linguistics phone: (301) 405-8903
College Park, MD 20742 USA	   Fax: (301) 314-2644 / (301) 405-7104
http://umiacs.umd.edu/~resnik	   E-mail: resnik AT umd _DOT.GOES.HERE_ edu

Course Info for Ling773/CMSC773/INST728C, Spring 2013 Computational Linguistics II