Module 06-11223 (2010)
Natural Language Processing & Applications
|Mark Lee||Semester 2||10 credits|
Co-ordinator: Mark Lee
Reviewer: Nicholas Hawes
The Module Description is a strict subset of this Syllabus Page.
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
On successful completion of this module, the student should be able to:
- show knowledge and understanding of the core theory underlying speech and natural language processing
- explain its relevance to specific applications
- show an understanding of some current applications of NLP, and evaluate them, demonstrating an appreciation of their strengths and weaknesses
2 hrs lectures per week plus 6 labs/tutorials
- Sessional: 1.5 hr examination (80%), continuous assessment (20%).
- Supplementary: By examination only (100%)
- 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.