Course Information
Instructor information
Professor
- Name:
- David N. Chin
- Email:
- chin@hawaii.edu
- Office:
- POST 303C
- Office Hours:
- Mondays and Fridays 8:30-11 and by appointment
- Office Phone:
- 956-8162
Topic
From the catalog: Current issues in artificial intelligence, including expert systems, knowledge representation, logic programming, learning, natural language processing. This semester, the emphasis will be on natural language processing.
Prerequisites
ICS 461, Artificial Intelligence, or consent.Textbooks
- required: Speech and Language Processing, 2nd edition by Daniel Jurafsky and James H. Martin, Prentice Hall, 2008, ISBN-10: 0131873210, ISBN-13: 978-0131873216.
Grading Policy
The grade will be based 20% on assignments, 15% on weekly take-home quizzes, 15% on the Midterm exam, 25% on the Final exam, and 25% on the final project. There will most likely be four assignments, all in the first half of the semester, so that the second half of the semester is free for your final projects (either individual or small group projects of up to 3 students).
Quizzes
The take-home quizzes will be graded as pass (100% credit) or fail (0 credit) with a pass given if you show a reasonable effort toward the solution (so you do not have to get the correct solution for a pass). Quizzes can be turned in either electronically by uploading them to Laulima before the start of class or on paper at the very start of class. Quiz questions will reappear in the Midterm and Final exams with very slight modifications (e.g. changing the numbers of the question parameters), so it will be wothwhile spending the time to work out the quiz problems.
Exams
The Midterm exam will cover all material prior to the Midterm date and the Final exam will be comprehensive. Only modified quiz questions will appear on the Midterm and Final exams, so everyone should ace the exams!
Assignments
You may use one of the following object-oriented programming languages for your assignments and project: Common LISP, C++, C#, Smalltalk, Java, Eiffel, Ruby, Python. If you would prefer another object-oriented language, discuss it with me first. Note: Perl and Visual Basic, despite having "objects", are so compromised that they cannot be considered good object-oriented languages, so will not be acceptable languages for this class.
Final Project
The 25% final project requires a presentation on the last day of class (10%) and a report (15%). The presentation will be on the last day of class with 10 minutes for the actual presentation and 5 minutes for questions. All students in a group project must participate in the presentation approximately equally. The grading of the presentation is broken down into content (7%) and delivery (3%) following the UH Oral Presentation Evaluation Form.
The final report should include:
- an Introduction that describes your problem, its subject area and scope (similar to your proposal). What were the goals of your project?
- a Description of the details of what you actually did including references to any resources that you used (software, corpora, articles, textbooks, etc.). What problems did you run into during your project and how you solved them? Some of your solutions may have been "hacks" that you were forced to use because of time/resource constraints, which is fine, but you should describe the correct approach if you were given enough time/resources. What NLP/AI techniques did you use? What design decisions did you make in your project and why? If applicable, what NLP/AI tools did you use and why did you choose those tools?
- an Analysis section that detail how well your project works (what it does well and what it does poorly) and how it compares to other similar efforts. How well did you achieve the goals described in the Introduction?
- a Conclusion that summarizes what you learned and suggestions for others who might want to repeat your work or extend it.
- a Bibliography and one or more Appendices containing your commented object-oriented source code (if any), data and sample runs with annotations explaining the run.
The 15% report grading is broken down into content (10%) and presentation/organization (5%). The final report is due by email before the last day of classes and will be posted on the class website. Finally, each student will participate in grading other students. A student's grade will be computed as the average of the grades from all other students and the instructor after dropping the highest and lowest presentation grades and the highest and lowest report grades. The presentation grades are collected on the last day of class and the report grades are due by email before the final exam. Failure to participate in grading will be penalized by a 33% deduction on your project grade. I will compile and anonymize the comments and grades from both the presentation and the report and send these to the graded student.
David N. Chin / Chin@Hawaii.Edu