COMP 4221/5221 - Fall 2013

Fall 2013, COMP 4221 Introduction to Natural Language Processing [3-0-1:3]
Fall 2013, COMP 5221 Natural Language Processing [3-0-0:3]
Lecture 1, WeFr 16:30-17:50, Rm 4504 at L25/26
Prof. Dekai WU, Rm 3539, 2358-6989, dekai@cs.ust.hk

Lab 1A TA: Karteek ADDANKI, Fr 10:30-11:20, Rm 2463 at L25/26, vskaddanki@cs.ust.hk

You are welcome to knock on the door of the instructor any time. The TAs' office hours are posted at http://course.cs.ust.hk/comp4221/ta/.

ANNOUNCEMENTS

Welcome to COMP4221 for UGs and COMP5221 for PGs! (The COMP4221 course was formerly called COMP300H and COMP326, and the COMP5221 course was formerly called COMP526.) Tutorials will begin after Week 2.

Always check the Discussion Forum for up-to-the-minute announcements.

Discussion forum is at http://comp151.cse.ust.hk/~dekai/content/?q=forum/3. Always read before asking/posting/emailing your question. This forum is based on modern software, instead of using the old clunky ITSC newsgroup. You must register for your account at the first lecture, tutorial, or lab.
Course home page is at http://www.cs.ust.hk/~dekai/4221/.
Tutorial info is at http://course.cs.ust.hk/comp4221/ta/.

ORIENTATION

Abbreviated Course Catalog Description

COMP 4221. Human language technology for text and spoken language. Machine learning, syntactic parsing, semantic interpretation, and context-based approaches to machine translation, text mining, and web search.

COMP 5221. Techniques for parsing, interpretation, context modeling, plan recognition, generation. Emphasis on statistical approaches, neuropsychological and linguistic constraints, large text corpora. Applications include machine translation, dialogue systems, cognitive modeling, and knowledge acquisition. Background: COMP 3211 or equivalent.

Course Description

Human language technology for processing text and spoken language. Fundamental machine learning, syntactic parsing, semantic interpretation, and context models, algorithms, and techniques. Applications include machine translation, web technologies, text mining, knowledge management, cognitive modeling, intelligent dialog systems, and computational linguistics.

TEXTBOOKS

HONOR POLICY

To receive a passing grade, you are required to sign an honor statement acknowledging that you understand and will uphold all policies on plagiarism and collaboration.

Plagiarism

All materials submitted for grading must be your own work. You are advised against being involved in any form of copying (either copying other people's work or allowing others to copy yours). If you are found to be involved in an incident of plagiarism, you will receive a failing grade for the course and the incident will be reported for appropriate disciplinary actions.

University policy requires that students who cheat more than once be expelled. Please review the cheating topic from your UST Student Orientation.

Warning: sophisticated plagiarism detection systems are in operation!

Collaboration

You are encouraged to collaborate in study groups. However, you must write up solutions on your own. You must also acknowledge your collaborators in the write-up for each problem, whether or not they are classmates. Other cases will be dealt with as plagiarism.

GRADING

The course will be graded on a curve, but no matter what the curve is, I guarantee you the following.

If you achieve 85% you will receive at least a A grade.
75% B
65% C
55% D

Your grade will be determined by a combination of factors:

Midterm exam ~20%
Final exam ~25%
Participation ~5%
Assignments ~50%

Examinations

No reading material is allowed during the examinations. No make-ups will be given unless prior approval is granted by the instructor, or you are in unfavorable medical condition with physician's documentation on the day of the examination. In addition, being absent at the final examination results in automatic failure of the course according to university regulations, unless prior approval is obtained from the department head.

There will be one midterm worth approximately 20%, and one final exam worth approximately 25%.

Participation

Science and engineering (including software engineering!) is about communication between people. Good participation in class and/or the online forum will count for approximately 5%.

Assignments

All assignments must be submitted by 23:00 on the due date. Scheme programming assignments must run under Chicken Scheme on Linux. Assignments will be collected electronically using the automated CASS assignment collection system. Late assignments cannot be accepted. Sorry, in the interest of fairness, exceptions cannot be made.

Programming assignments will account for a total of approximately 50%.

Tutorials

All information for tutorials is at http://course.cs.ust.hk/comp4221/ta/.

SYLLABUS

Date Wk Event Topic
 


2013.09.04 1 Lecture Does God play dice? Assumptions: scientific method, hypotheses, models, learning, probability
Admiinistrivia (honor statement, HKUST classroom conduct)
2013.09.06 1 Lecture Languages of the world
2013.09.11 2 Lecture Linguistic relativism and the Sapir-Whorf hypothesis; inductive bias, language bias, search bias; the great cycle of intelligence
2013.09.12 2 Lecture Is machine translation intelligent? Interactive simulation [20:00 Lab 3]
2013.09.13 2 Lecture Learning to translate: engineering, social, and scientific motivations [at tutorial]
2013.09.13 2 Lecture "It's all Chinese to me": linguistic complexity; challenges in modeling translation
2013.09.18 3 Lecture [rescheduled to previous 2013.09.12 session]
2013.09.20 3 Holiday Mid-Autumn Festival
2013.09.25 4 Lecture Evaluating translation quality: adequacy, fluency, fidelity, speed, memory, n-grams, BLEU
2013.09.26 4 Lecture Machine translation in Macau [14:30 LTH]
2013.09.27 4 Lecture Evaluating translation quality: case frames, semantic frames, semantic role labeling, predicate-argument structure [at tutorial]
2013.09.27 4 Lecture Evaluating translation quality: alignment; aligning semantic frames
2013.10.02 5 Lecture Anagrams; bag translation
2013.10.04 5 Lecture Markov models, n-gram models
2013.10.09 6 Lecture Uninformed search; Dijkstra's shortest path algorithm
2013.10.11 6 Lecture Anagrams with replacement; Chinese anagrams; word n-grams
2013.10.16 7 Lecture HMM/SFSA/WFSA: hidden Markov models, finite-state models; parts of speech; generation vs recognition/parsing; converting state-based to transition based FSAs
2013.10.18 7 Lecture [rescheduled to previous 2013.09.13 session]
2013.10.23 8 Lecture HMM/SFSA/WFSA: formalization for Viterbi decoding and evaluation [slides]
2013.10.25 8 Exam Midterm
2013.10.28 9 Lecture Making sense in translation: Addressing lexical choice errors when translating across domains [16:00 LTF]
2013.10.30 9 Lecture HMM/SFSA/WFSA: forward algorithm, backward algorithm, expectations
2013.11.01 9 Lecture HMM/SFSA/WFSA: forward-backward algorithm, expectation maximization (EM) algorithm
2013.11.06 10 Lecture Segmental HMM/SFA/WFSAs; WFST: finite-state translation models
2013.11.08 10 Lecture AND/OR graphs; FSGs (finite-state grammars); segmental FSGs
2013.11.13 11 Lecture Sentence alignment [chapter]
2013.11.15 11 Lecture CFGs (context-free grammars); segmental CFGs
2013.11.20 12 Lecture Syntax-directed transduction grammars
2013.11.22 12 Lecture Inversion transduction grammars [article]
2013.11.27 13 Lecture The magic number 4: how the generative capacity of ITGs explains the evolution of semantic frame structure
2013.11.29 13 Lecture Bracketing inversion transduction grammars (BITGs): alignment, bibracketing, translation-driven segmentation, learning phrasal translation lexicons, projection/coercion, EM [article]
2013.11.29 13 Lecture ITGs: translation, incorporating language models [article]; general, linguistic, and non-binary rank ITGs [article] [18:00 Rm 3401]
2013.12.11 14 Exam COMP5221 Final [Rm 2464, L25-26, 12:30-15:30]
2013.12.12 14 Exam COMP4221 Final [Rm 2405, L17-18, 16:30-19:30]

Background review



dekai@cs.ust.hk
Last updated: 2013.12.04