Course web page:
http://www.eng.utah.edu/~cs6961
The course web page will contain pointers to the syllabus, lecture slides,
assignments, solutions, and project information.
COURSE OBJECTIVES
The goals for this course are to study methods for extracting
different types of information from natural language text. We will
study algorithms to extract semantic concepts (e.g., named entities,
hypernym/hyponym classes, semantic roles), facts (e.g., event roles,
event chains, relations), and opinions (e.g., sources, targets). The
course will include methods for extracting information from text
corpora as well as the Web, and will emphasize applications for both
broad-coverage and domain-specific information extraction. The class
will involve a substantial project to give everyone hands-on experience
building a real information extraction system.
GRADING POLICY
Grades for the course will be based on written and programming assignments,
a midterm exam, and a project. Overall grades will be based on the
following weighting scheme:
- Written Assignments: 20%
- Programming Assignments: 20%
- Midterm Exam: 20%
- Project: 40%
Homework assignments must be submitted using the electronic
handin system, including BOTH written and programming assignments. The
written assignments must be submitted in pdf format. Instructions for
using the electronic handin system will accompany each
assignment. Assignments slipped under a door or left in the main
office will not be accepted.
You can use any of the following programming languages: perl, python,
or Java. You must get permission from the instructor if you wish to
use any other programming language.
CADE LAB
All programs
must compile and run on the unix-based
CADE machines. You will receive
ZERO credit for programs that do not compile and run on the unix-based
CADE
machines. This policy is necessary for the instructor to be
able to test and grade your programs ourselves.
LATE POLICY
All assignments must be submitted promptly by the due date, or they
will be accepted up to 24 hrs after the due date but will be
assessed a 10% late penalty. For example, if you turn in your code
late and it earns a score of 92, then your actual grade will be 92 -
9.2 = 82.8 . No assignments will be accepted more than 24 hrs after the
due date. Our primary motivation for this is to ensure that
assignments are graded and returned as quickly as possible. Allowing
late assignments holds up the grading process and the distribution of
solutions. We will do our best to grade the assignments and hand out
solutions quickly so that everyone will get feedback in a timely
fashion. This policy also ensures that you have sufficient time to
work on the next assignment without getting bogged down by the
previous one.
Please note that we will adhere very strictly to the timestamps that
show when your files were turned in! If an assignment is due by
midnight and your file is stamped 12:05am, then you will be assessed
the 10% late penalty. This may sound harsh, but we have to draw a
line somewhere. To get the best grades possible, we offer the
following advice:
* You can submit files as often as you like, so always make sure
to submit something before the due date!
* If you discover a major bug or finish solving a problem
within 24 hrs after the due date, and you believe that your new
solution is substantially improved over your original solution,
then resubmit new files! In this case you will be assessed the 10%
late penalty, but your new solution will probably earn you a
better score, so even with the late penalty you will end up with a
higher grade.
* Always, always, ALWAYS submit something within 24 hrs of the due
date, or we will have no choice but to give you a zero. A zero
will wreak havoc on your average! Even if you only receive partial
credit for an assignment, your overall average in the class will
not suffer nearly as much as if you got a zero.
CHEATING POLICY
Cheating of any kind will not be tolerated. If you are caught
cheating, you will receive a failing grade sanction for the
class. All assignments, programs, and exams must be your own
work!
Everyone in this class should read the
School
of Computing's Policy on Academic Misconduct and must sign the
School of
Computing Academic Misconduct Policy Acknowledgement Form.
IMPORTANT: if you receive two failing grade sanctions in CS courses
due to academic misconduct then you will be immediately dropped from
any School of Computing degree program and will not be allowed to
register for any other CS courses in the future.
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 copy someone else's solution, you are cheating.
If you let someone else copy your solution, you are cheating.
We will not distinguish between the person who copied a
solution and the person whose solution was copied. Both people
will be treated as cheaters.
- 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. We strongly encourage
students to help one another understand the material presented
in class, in the book, and general issues relevant to the
assignments.
- When taking an exam, you must work independently. Any collaboration
during an exam will be considered cheating.
- Any student who is caught cheating will be given an E in the course and
referred to the University Student Behavior Committee. Many
students think they can get away with cheating and will not be
caught. But it is much easier to spot cheaters than you might
think! Please don't take that chance - if you're having
trouble understanding the material, please let us know and we
will be more than happy to help.
If you are having trouble
understanding the material or completing an assignment, please don't
hesitate to ask the instructor for help ... that's what we're
here for!
AMERICANS WITH DISABILITIES ACT (ADA)
The University of Utah seeks to provide equal access to its
programs, services and activities for people with disabilities. If
you will need accommodations in the class, reasonable prior notice
needs to be given to the Center for Disability Services, 162 Olpin
Union Building, 581-5020 (V/TDD). CDS will work with you and the
instructor to make arrangements for accommodations.
All written information in this course can be made available in
alternative format with prior notification to the Center for
Disability Services.
COLLEGE OF ENGINEERING GUIDELINES
COE course guidelines on add/drop periods, etc. can be found at:
College of Engineering Guidelines, Spring 2014