|
|
CS 224N -- Ling 237: Natural
Language Processing |
Meeting Times and Locations
Lecture: 3-4 units, MW 1:15-2:30 in
Mitchell Earth Sciences B67
Section: 0 units, TBA
The sections will work through concrete problems
and examples of the sort that appear on homework and programming assignments,
discuss solutions to questions, and provide necessary background in probability,
corpora, and linguistics, as needed.
You are strongly encouraged to attend section for a better understanding
of the course content.
Electronic Communications
|
Course web page: |
Most of the useful information is here. Including the FAQ! |
|
|
Newsgroup: |
This is intended for general discussion, assignment hints,
people looking for partners, etc. |
|
|
Announcement mailing lists: |
cs224n-spr0304-students@lists.stanford.edu |
This list is intended for important announcements for all
students. You will be automatically subscribed to this list when you enroll in the class.. |
|
|
cs224n-spr0304-guests@lists.stanford.edu |
If you are not formally enrolled in the class, you should subscribe to cs224n-spr0304-guests
to receive the same announcements. Send an email with “subscribe cs224n-spr0304-guests” in the body to majordomo@lists.stanford.edu. If possible, please
subscribe from a leland account, as this will allow you to access Stanford corpora, which will be
necessary for assignments. |
|
Questions mailing list: |
Send your questions here! |
If you have a question:
- Check out the Frequently Asked Questions list! The answer to your question might already be posted.
- For any regular questions about the course, the homework assignments, the programming projects, etc., use cs224n-spr0304-staff@lists.stanford.edu to email the instructor and TAs all at once.
- You will get a much quicker response if you email this address than if you email one particular person individually.
- We will try to answer all emails, but we cannot guarantee to answer questions sent less than 6 hours before an assignment is due.
- Before sending an email about an assignment, read the whole question and spend some time thinking about it.
- Be sure to check the FAQs before sending an email!
- Come to office hours! This is the easiest way to get a question answered - especially if you need a more detailed explanation of things.
- We welcome all comments and suggestions about the course!
Teaching Staff
|
Professor: Christopher Manning Phone: (650) 723-7683 E-mail: manning@cs.stanford.edu Professor Manning works primarily on systems that can intelligently process and produce human languages. His interests include probabilistic models of language and statistical natural language processing, constraint-based theories of grammar, computational lexicography, syntax, and information extraction. |
|
|
TA: Jeanette Pettibone |
|
|
TA: Praveen Kankanala |
|
|
Course admin: Sara Weden |
|
Course Objective
To introduce students to both fundamental concepts in natural language processing (NLP) as well as current research in the area.
Course Description
This course helps students develop an in-depth understanding of the algorithms available for processing linguistic information and the underlying computational properties of natural languages. It covers morphological, syntactic, and semantic processing from both a linguistic and an algorithmic perspective. The focus is on modern quantitative techniques in NLP: using large corpora, statistical models for acquisition, disambiguation, and parsing. Also, it examines and constructs representative systems.
Prerequisites
- Adequate experience with
programming and formal structures (e.g., CS106 and CS103X). Programs will be written in Java, so
knowledge of Java (or a willingness to learn on your own) is required.
- Knowledge of standard
concepts in artificial intelligence and/or computational linguistics
(e.g., CS121/221 or Ling 138/238).
- Basic familiarity with logic,
vector spaces, and probability.
Intended Audience
Graduate students and advanced undergraduates
specializing in computer science, linguistics, or symbolic systems.
Course Materials
The required text is
- Christopher Manning and
Hinrich Schütze,
Foundations of Statistical Natural Language Processing. MIT Press, 1999. ($75.00 list price [currently out of stock at the bookstore until April 19]; $63.75 from amazon.com.)
Read the text online!Please see http://nlp.stanford.edu/fsnlp/ for supplementary information about the text, including errata, and pointers to online resources.
The following text are useful but optional:
- James Allen. 1995. Natural Language Understanding. Benjamin/Cummings, 2ed.
- Gerald Gazdar and Chris Mellish. 1989. Natural Language Processing in X. Addison-Wesley.
- Dan Jurafsky and James Martin. 2000. Speech and Language Processing. Prentice Hall.
Additional handouts and papers will occasionally be distributed and discussed during the course of the class. Electronic copies (when available) can be accessed either from the syllabus or in this directory. Hard copies will be available outside Gates 419 (in front of Prof Manning's room) while supplies last.
Hardware/Software Requirements
Students may use their own computers or their Stanford Leland accounts. Students will need to submit assignments using the Leland Unix systems. Materials for class assignments will be made available via AFS, and so access to files there will also be required. We will run and evaluate systems on the Leland Unix machines, so they must run correctly on those machines.
Work and Grading
7 Homework assignments : 10 points each (70% of your grade)
- All homework will be due at 5pm, prevailing Pacific time on the dates assigned. You are encouraged to submit your written homework during class, but don't skip class just because you haven't finished it. If not handed in in class, you should give your homework to the course admin, the instructor, or the TA. There is also a box outside Chris Manning's office (Gates Rm. 418) where you can turn it in.
- Written homeworks and programming project write-ups need to be submitted on paper. We cannot accept written assignments by fax or email. Programs will be submitted electronically on the Leland systems. Solutions sets and graded problem sets will be handed out as soon as possible.
- Extra credit may be given to projects that go substantially above and beyond the requirements in finding creative solutions to the tasks, or which perform exceptionally well. Up to 5% extra credit may also be assigned for class or section participation.
- So that we can post written homework solutions reasonably promptly, you are limited to a maximum of 3 late days on any one written homework. Homework will not be accepted after solutions have been posted.
- All homework must be legible to be graded.
Final project : 30 points (30% of your grade)
- The final project may be a group project, but the amount of work should be appropriately scaled to the size of the group, and you should include a brief statement on the responsibilities of different members of the team. Team members will normally get the same grade, but we reserve the right to differentiate in egregious cases.
- You will be required to give a mini presentation on your project in the last class. You are also asked to submit an electronic copy of the final project write-up, so that we can make a class projects page.
- You can use at most 2 late days on the final project submission (the maximum deadline is the Friday of finals week - so that we can be done with grading in time, and can join you at the beach!). Also, late days on the final project will be counted differently - if a group of k people turns in the final project n days late, nk late days will be counted against each group member!
Homework Collaboration Policy
The wording here is a bit complex, but I think it makes sense. Please
ask if you have any questions, and make sure you adhere to it.
- You may talk to anybody you want about the assignments, including working through problems together in groups. Indeed, we encourage you to work in groups, and to work with different people through the quarter.
- However, for written problem sets:
- you must state on your written assignment the people you discussed problems with
- you are not allowed to take detailed notes in any group sessions that will appear verbatim in assignment write-ups. Everybody has to turn in written homework answers that are written solely by himself/herself.
- Programming parts/projects: These can be done by oneself or in groups of at most 3, and people may submit a joint submission or identical material, which is assumed to be the joint work of all partners.
Late Days
To accommodate possible emergencies, you are given 7 late days (calendar days) to use at your discretion in 24 hour increments. You are expected to keep late days for real emergencies. If you exceed the allowed number, pointswill be deducted at the rate of 10% per day or part thereof.
Policy on Regrades
We do make every effort to ensure that your assignment is graded right the first time! However, sometimes people miss things, or there can be disagreements in interpretation. If you're unhappy with the grade for a question, you need to make a written request for a regrade and to resubmit your entire homework, either to one of the TAs or to the instructor. The request doesn't have to be formal and long. Simply writing on a sheet of paper "8 points were taken off question 3, but I think it's a perfectly valid answer to the question" is sufficient. Normally, the TA will regrade it. If you're still not happy, you should repeat this process, but indicate that you want the instructor to re-regrade it. Negating this policy: you should not e-mail grading complaints, and you can't expect assignments to be regraded "while you wait".
Pass/No Credit
The course may be taken Pass/No Credit if desired - the grade will then be evaluated using the same criteria, and you must make sure you submit enough work to get to a Pass grade.Honor Code
All actual, detailed work on the solution of problem sets must be individual work. You are encouraged to discuss problem sets with each other in a general way, but if you do so, then you must acknowledge the people who you discussed the problem set with at the start of your solutions. You should not look for problem answers elsewhere, but again, if material is taken from elsewhere, then you should acknowledge it. For programming projects, you are not permitted to get programming help from other people. Normally, you are permitted to use pre-existing code, but you must acknowledge code that you have taken from other sources. You will only be evaluated on code that you have written for the project, so it is not in your interests to find code that implements the core algorithms for the project. In general, we will act and expect you to act according to the Stanford Honor Code.
Home
Page
Last modified: Mon Apr 14 14:41:30 PDT 2004