SYLLABUS PAGE, 2007/08
06-11223
Natural Language Processing & Applications
Level 3/H
|
Dr P Coxhead |
10 credits in Sem1 |
Programmes | Modules | Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus
The School of Computer Science Module Description is a strict subset of this Syllabus Page. (The University module description has not yet been checked against the School's.)
Relevant Links
See the NLPA web site for all handouts, more links, etc.
Outline
| The module will cover: levels of NLP, speech (phonetics, phonology); grammar (morphology, syntax); meaning (semantics, pragmatics); applications (text-to-speech, speech-to-text, parsing, MT, NL interfaces). The emphasis will be on the background needed to understand practical applications of speech and natural language processing. |
Aims
The aims of this module are to:
- Introduce students to the basics of natural language processing (including speech), with an emphasis on its practical applications.
- Cover enough of the linguistic and computing background to allow understanding and evaluation of some applications, such as speech synthesis, speech recognition or machine translation.
Learning Outcomes
| On successful completion of this module, the student should be able to: | Assessed by: | |
| 1 | Show knowledge and understanding of the core theory underlying speech and natural language processing. | Continuous Assessment, Examination |
| 2 | Explain its relevance to specific applications. | Continuous Assessment, Examination |
| 3 | Show an understanding of some current applications of NLP, and evaluate them, demonstrating an appreciation of their strengths and weaknesses. | Continuous Assessment, Examination |
Restrictions, Prerequisites and Corequisites
Restrictions:
| None |
Prerequisites:
| None |
|
Knowledge of a programming language is assumed. Neither 06-02495 Natural Language Processing 1 nor 06-02630 Software Workshop Prolog are prerequisites, although there will be a small amount of common material. You will need to be willing to grapple with the complexities of natural language, including learning some basic phonetics and linguistics. A knowledge of another language can help, although it isn't essential. |
Co-requisites:
| None |
Teaching
Teaching methods:
| 2 hrs lectures per week plus 6 labs/tutorials |
Contact hours:
| 30 |
Assessment
Normal (sessional): 1.5 hr examination (80%), continuous assessment (20%).
Resit (supplementary) (where allowed): As the normal assessment.
Recommended Books
| Title | Author(s) | Publisher, Date | Comments |
| Lecture Notes | Coxhead, P | There isn't a current text which covers this module very well; detailed handouts are available. | |
| Foundations of General Linguistics (2nd ed.) | Atkinson, M, Kilby, D A & Roca, I | London: Unwin Hyman, 1988 | Currently the best text for linguistics background. |
| An Introduction to Language (5th ed.) | Fromkin, V & Rodman, R | Holt, Rinehart & Winston, 1993 | Linguistics background reference. Livelier than Atkinson et al. but American and so NOT to be used for phonetics! |
| Speech and Language Processing | Jurafsky, D. & Martin, J.H. | Prentice Hall, 2000 | Reference; probably the best overall coverage currently available. |
| Natural Language Understanding (2nd ed.) | Allen, J | Benjamin/Cummings, 1995 | Comprehensive, but strongly oriented towards Lisp and predicate calculus for semantic representation. Also very parochial in its neglect of languages other than English. |
| Natural Language Processing for Prolog Programmers | Covington, M A | Prentice-Hall, 1994 | Reference; some relevant material for those with a knowledge of Prolog. |
| Natural language processing in Prolog: an introduction to computational linguistics | Gazdar, G & Mellish, C | Addison-Wesley, 1988 | Reference; a 'classic' for those with appropriate prior knowledge. (There's a parallel book in Lisp.) |
Detailed Syllabus
- Introduction. What is 'natural language'? Definitions, 'levels' of language processing, dialects and language changes. 1 week.
- Phonetics & phonology. Linguistic concepts -- phonemes, allophones, feature sets, phonological rules. The phonemes of English ('Standard English English' and 'Standard American English') and their representation in the IPA. Applications in speech synthesis (TTS) and speech recognition (STT). Whole word, grapheme-phoneme-allophone and biphone synthesis techniques. Language models in speech recognition. Introduction to further issues, including stress and intonation. 3 weeks.
- Morphology. Introduction to morphology in both spoken and written language. Definitions -- morpheme, inflectional and derivational morphology. Applications, including spelling checkers. 1 week.
- Syntax. Brief overview of the grammar of English (noun phrase, verb phrase, sentence). Outline of Phase-Structure Grammars using Prolog notation, approaches to generation and parsing (not algorithms). Syntax trees. Application to Machine Translation. 3 weeks.
- Meaning. Semantic features and their applications. 'Case' / thematic roles. The limitations of current approaches to semantic processing -- anaphora, ellipsis, etc. Brief introduction to pragmatics. 3 weeks.
Programmes | Modules | Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus