Natural Language Processing
Björn Gambäck
<gamback@sics.se>
Gunnar Eriksson
<gunnar@ling.su.se>
Athanassia Fourla
<afourla@hotmail.com>
Visiting hour
by appointment
Course material
available for copying in the department's course material bookshelf.
- Books
- Articles
- Other material
Lecture schedule
Examination
- Written account of the five lab assignments.
Send them in by Wednesday 17.3 (NB!).
- A written exam Tuesday 9.3, 10:00 (NB!).
(Exam feedback: Thursday 11.3, 14:00.)
- The course grade will be assigned as follows:
exam 55%, assignment 1 5%, assignments 2-5 10% each.
Course material
Books
Daniel Jurafsky and James H. Martin (J&M)
SPEECH and LANGUAGE PROCESSING:
An Introduction to Natural Language Processing,
Computational Linguistics, and Speech Recognition
Prentice-Hall, 2000.
Reading Instructions:
Ch. 1;
Ch. 2;
Ch. 3;
Ch. 4, pp. 91-112, 120-133;
Ch. 6;
Ch. 7.1-7;
Ch. 8;
Ch. 9;
Ch. 10;
Ch. 11.1-3;
Ch. 12.4-5;
Ch. 14, pp. 501-527;
Ch. 15.1-2, 4-5;
Ch. 16;
Ch. 17;
Ch. 18.1-3;
Ch. 19;
Ch. 20.1-2;
Ch. 21
Articles
Douglas Arnold et al. 1994:
Machine Translation: An Introductory Guide, Ch. 3, 4, 6, 8, 9.
Björn Gambäck 1999:
Human Language Technology: The Babel Fish
(pdf) (ps)
John Kimball 1973:
"Seven Principles of Surface Structure Parsing in Natural Languages",
Cognition 2(1), pp. 15-47.
Yorick Wilks & Roberta Catizone 2000:
"Human-Computer Conversation",
Encyclopedia of Microcomputers, Dekker, New York.
Victor Zue & James Glass 2000:
"Conversational Interfaces: Advances and Challenges",
Proceedings of the IEEE 88(8), pp. 1166-1180.
Other material
Nikolaj Lindberg
egrep for Linguists
Jurafsky and Martin
Links to NLP resources
Amharic Links
Lecture Schedule
| | time
|
|---|
| Lecture 1: Introduction, Language | Fri Jan 16, 2:00 pm
| | Lecture 2: Language structure, NLP | Mon Jan 19, 3:00 pm
| | Computer lab 1 (1) | Fri Jan 23, 2:00 pm
| | Lecture 3: Phonology and Morphology | Mon Jan 26, 3:00 pm
| | Computer lab 1 (2) | Tue Jan 27, 8:30 am
| | Lecture 4: Computational Morphology | Tue Jan 27, 3:00 pm
| | Computer lab 1 (3) | Wed Jan 28, 8:30 am
| | Computer lab 2 (1) | Fri Jan 30, 2:00 pm
| | Lecture 5: Words, their neighbors, and POS | Mon Feb 2, 3:00 pm
| | Computer lab 2 (2) | Tue Feb 3, 8:30 am
| | Lecture 6: POS Tagging | Tue Feb 3, 3:00 pm
| | Computer lab 2 (3) | Wed Feb 4, 8:30 am
| | Computer lab 3 (1) | Fri Feb 6, 2:00 pm
| | Lecture 7: The meaning of words | Mon Feb 9, 3:00 pm
| | Computer lab 3 (2) | Tue Feb 10, 8:30 am
| | Computer lab 3 (3) | Tue Feb 10, 3:00 pm
| | Computer lab 3 (4) | Wed Feb 11, 8:30 am
| | Lecture 8: NLP systems, Overview | Fri Feb 13, 2:00 pm
| | Lecture 9: Machine Translation I | Mon Feb 16, 3:00 pm
| | Lecture 10: Machine Translation II | Tue Feb 17, 3:00 pm
| | Lecture 11: Basic Grammars | Thu Feb 19, 2:00 pm
| | Lecture 12: Parsing | Fri Feb 20, 2:00 pm
| | Lecture 13: Features and Unification | Mon Feb 23, 3:00 pm
| | Computer lab 4 (1) | Sat Feb 28, 3:00 pm
| | Computer lab 4 (2) | Mon Mar 1, 10:00 am
| | Lecture 14: Semantics | Mon Mar 1, 3:00 pm
| | Computer lab 4 (3) | Tue Mar 2, 10:00 am
| | Lecture 15: Pragmatics | Tue Mar 2, 3:00 pm
| | Computer lab 5 (1) | Wed Mar 3, 10:00 am
| | Computer lab 5 (2) | Thu Mar 4, 10:00 am
| | Lecture 16: Speech | Thu Mar 4, 3:00 pm
| | Written Exam | Tue Mar 9, 10:00 am
| | Computer lab 5 (3) | Wed Mar 10, 10:00 am
| | Computer lab 5 (4) | Thu Mar 11, 10:00 am
| | Exam Feedback | Thu Mar 11, 2:00 pm
|
Introduction; Administrative details; Language and languages;
Relations between languages; Written and spoken languages
Human language and other types of communication; The structure of language; What is NLP?
| Slides
|
| To read
|
| Other relevant material
|
|
|
| J&M Ch. 1
|
|
|
Phonemes; Syllables; Writing systems; Transliteration
Regular expressions; Finite state automata; Morphology
| Slides
|
| To read
|
| Other relevant material
|
|
|
| J&M Ch. 4, pp. 91-112
J&M Ch. 2, pp. 19-53
J&M Ch. 3, pp. 57-65
|
| Any description of Amharic morphology
J&M links to NLP resources
|
Morphology; Regular languages; Finite state tranducers; Two-level morphology; Stemming; Morphological parsing
Words; Tokenization; Counting words; Types and Tokens; Syntax;
Phrases; Collocations; N-grams; Sparse data; Part-of-speech category
and syntactic function; Open and closed classes; Lexical and
grammatical words; Tagsets; Ambiguity
Methods for part-of-speech tagging; Unknown words; Evaluation; Precision - Recall
Lexemes; Relations between lexemes: homonymy, polysemy, synonymy, hyponomy; Thematic roles; Word sense disambiguation; Words and Information retrieval
Examination; Schedule for the second half of the course.
The components of an NLP system;
what do we need to build language processing systems?
| Slides
|
| To read
|
|
|
|
| J&M Ch. 1
Gambäck 1999: Human Language Technology: The Babel Fish
(pdf) (ps)
|
|
|
Machine Translation theory
Machine Translation systems, MT users, applications, evaluation
Context-free grammars; Definite Clause Grammars; Dependency Grammar.
Parsing with context-free grammars; top-down parsing; bottom-up parsing;
Well-formed substring tables; head-first parsing; charts; LR parsing;
Human language processing.
| Slides
|
| To read
|
| Other relevant material
|
|
|
| J&M Ch. 10, 12.5
Kimball. "Seven Principles of Surface Structure Parsing in Natural Languages"
|
| Martin Kay. 1989. "Head-Driven Parsing",
Proc. 1st Int. Workshop on Parsing Technologies. Pittsburgh.
Alfred Aho & Jeffrey Ullman. 1972.
Ch. 4.2: Tabular Parsing Methods.
The Theory of Parsing, Translation, and Computation. Prentice-Hall.
Masaru Tomita. 1986.
Ch. 2: Informal Description of the Algorithm.
Efficient Parsing for Natural Language. Kluwer Academic Press.
|
Feature structures, subcategorization, unification.
| Slides
|
| To read
|
| Other relevant material
|
|
|
| J&M Ch. 11.1-3, 12.4
|
| SWI-Prolog.
Patrick Blackburn, Johan Bos & Kristina Striegnitz. 2001.
Learn Prolog Now!.
Saarbrücken, Germany.
|
Semantic models, representing meaning.
Syntax-driven semantic analysis, quantifiers, compositionality.
Discourse processing, reference resolution, conversational agents, dialogue.
Automatic speech recognition, speech generation, text-to-speech synthesis.
Spoken dialogue systems, speech-to-speech machine translation.
Written Exam Tue Mar 9, 10:00 am
Exam Feedback (slides) Thu Mar 11, 2:00 pm
|