University of Mary Washington
Department of Computer Science
CPSC370: Computational Linguistics Seminar
Wednesday 6-8:45pm Trinkle B6
Because this class meets for 2.75 hours once per week we have some challenges. One is that 2.75 hours is a long time to stay focused on only one activity–for example, listening to a 2.75 hour lecture. To help keep our energy up in each class we will be moving from one activity to another (for example, a short lecture followed by a seminar-like discussion on a reading, followed by hands-on activities like developing a finite state morphological analyzer). The other problem with a 2.75 hour once-per-week class is the week-long gap between classes. To keep our interest up between classes we will participate in some sort of stream communication. The exact form of this stream (Twitter, Google+, whatever) will be collaboratively determined at our first class. In this stream we will post link to articles related to the course content, questions, and responses to these posts.
One objective is for course participants to gain an understanding of a range of symbolic and statistical computational linguistics techniques, and to understand how these techniques can be used in digital humanities. Another is to attain the necessary development skills to program applications that have natural language processing components.
- to develop competencies in using basic statistical text approaches to digital humanities.
- to develop the ability to meet coding deadlines
- to acquire an understanding of the structure of human languages including
- to develop abilities in using statistical approaches to natural language processing including machine translation
- to develop skill in developing finite state morphological analyzers and parsers.
Grading is based on a method developed by Professor Lee Sheldon at Indiana University. It is based on obtaining experience points (XP). The number of XP determines what level you are at. You start the class with 0 XP at Level 0. The level you obtain at the end of the semester determines your final grade. Here is the chart:
I differ from Professor Sheldon in offering students options on how to accumulate XP. There will be opportunities to earn at least 2300XP during the course. This gives each individual some flexibility in what tasks to do. You gain XP working individually, with a partner, and with your team.
If you are at Level Zero when midterm grades are due I will report your work as unsatisfactory.
Research/Programming Project 750-850 XP
The major effort you will be making for the class will be working on designing and developing some cool idea you have (as long as it relates in some way to computational linguistics). For example, you may want to develop a finite state morphological analyzer for Chechen, a statistical machine translation system for Guarani, or an analysis of Tibetan manuscripts. Rarely are real research or software projects a one-person effort and for this project you can collaborate with one or more partners.
Exercises – 700-800 XP
At least once per week we will be working on exercises. Many of the exercises will be done with a partner. The instructions for some of these exercises might be vague (“use the Google Ngram Search Tool and see what interesting things you find”). Others will be very specific (“Given a list of Swahili words and their translations, develop a morphological analyzer using the Xerox Finite State Toolkit”). There will be a variety of activities worth between 50-75XP. The vast majority of team work will be done during class time. However, to get maximum points on a particular task you may need to meet occasionally outside of class
Reports -200-400 XP
Throughout the semester you will have opportunities to be first responder for one of the papers we will be reading in class. I will be using a four category scale: the first responder didn’t read the paper; the responder’s comments & presentation in some way; the responder quickly but accurately summarized the paper and presented a clear critique of the paper; the responder drew from other sources when discussing the paper.
Team Participation – about 100XP
Each student will rate the helpfulness of all members of their team. Individual team participation scores will be the sum of the points they receive from other members of their team. Each team member distributes 100 points to other members of the team. The average team participation score will be 100 points. The rater must differentiate some of their ratings (they cannot assign the same rating to all members).
Avatar names, pseudonyms, noms de plume
During the first week of class I will ask you for your avatar name, pseudonym, whatever. This is the name that will appear on the Experience Point Google Spreadsheet that will be viewable by everyone in the class. If you wish to remain anonymous, don’t share your avatar name with anyone. On the other hand, if you would like recognition for achieving level 10 as an example (“a big shout out to tera miner for achieving level 10”), you can share your name. The decision is yours. To further protect the anonymity of those who wish to remain anonymous, the spreadsheet will also be populated by fictitious avatar names.
Accommodations for students with special needs
Any student with a documented disability may receive a special accommodation to complete any requirements of this course. If you are have a disability or believe you have one you may wish to self-identify. You may do so by providing documentation to the Office of Disability Services located in Room 203 of George Washington Hall (Phone: Voice 540-654-1266, Fax: 540-654-1163). Appropriate accommodations may then be provided for you. If you have a condition that may affect your ability to exit the premises in an emergency or that may cause an emergency during class, you are encouraged to discuss this in confidence with me and/or anyone at the Office of Disability Services. This office can also answer any questions you have about the Americans with Disabilities Act (ADA).
I assume you are an ethical student and a person with integrity. I expect that you will follow the university honor code (seehttp://rosemary.umw.edu/CSHonorCode.html). Please use common sense and ask yourself what would a person with integrity do? To help you, I would like to make three comments related to this:
Plagiarism means presenting some other person’s work as your own. This can mean using some other person’s words without acknowledging their source, or using some other person’s ideas. Copying another student’s work (homework or exam) is also plagiarism. Plagiarism will minimally result in an automatic zero for that submission.
Collusion is unauthorized collaboration that produces work which is then presented as work completed independently by the student. Collusion includes participating in group discussions that develop solutions which everyone copies. Penalties for plagiarism and collusion include receiving a failing grade for the course.
I ask that you respect the other people in the class. I recognize that your life circumstances may require you to receive cell phone calls during class. If this is the case please set your cell phone on vibrate and discretely leave the class to accept calls. During tests, if you walk out of the classroom, or consult/display your cell phone, I will assume you are done with the test and collect your grading sheet.
I expect students to attend classes regularly. That said, attendance is not taken and no XP will be awarded based directly on attendance. If you are going to miss a class, please be courteous and inform your team mates.
The class schedule is posted on the course website.