CSA3180 Natural Language Processing

1
CSA3180Natural Language Processing

• Introduction
• and
• Course Overview

2
Acknowledgement

• Material for some of these slides taken from J
  Nivre, University of Gotheborg, Sweden

3
Why Language and Computers

• Engineering
• NLP is concerned with the design and
  implementation of effective NL input and output
  components for computational systems (Robert Dale
  2000)
• Scientific
• The use of computers for linguistic research and
  applications

4
NLP is Interdisciplinary

• Linguistics
• Theoretical
• Applied
• Computer Science
• Algorithms
• Compiling Techniques
• Artificial Intelligence
• Understanding, reasoning
• Intelligent Action

5
Uszkoreits (2000) Five Points

• Solving the human language puzzle
• by implementing complex theories directly
• Teaching computers to communicate with people
• by exploiting natural modes of communication
• Friendly software should listen and speak
• through development of multimodal communication
• Machines can help people communicate with each
  other.
• by developing multilingual applications
• Language is the fabric of the web
• through language technology for knowledge
  management

6
Application Areas

• Document Processing
• Classification
• Summarisation
• Information Extraction
• Question Answering
• Information Retrieval
• Dialogue
• Multilinguality
• Machine Translation
• Translation tools
• Multimodality
• speech
• intonation
• image

7
Basic Problems

• Analysis
• Conversion of NL input to internal
  representations
• Generation
• Conversion of internal representations to NL
  output
• Issues
• What kind of input/output/representations
• Evaluation
• Learning

8
Levels of Linguistic Knowledge

• Phonetics/Phonology sound structure
• Morphology word structure
• Syntax sentence structure
• Semantics meanings
• Pragmatics use of language in context
• Discourse paragraphs, texts, dialogues

9
Ambiguity

• Morpho-SyntacticWe saw her duck
• Lexical SemanticThey went to the bank
• Structural semanticYoung men and women
• ReferentialShe did it
• PragmaticCan you pass the salt

10
Ways of Studying NLP

• By ApplicationMT, IE, IR etc.
• By Approachrational vs. empirical
• By Linguistic Levelmorphology, syntax etc.
• By Algorithm

11
Algorithms

• State Machines
• automata and transducers
• Rule Systems
• regular and context free grammars
• Search
• top-down/bottom-up parsing
• Probabilistic algorithms

12
Approach in this CoursePart I - Algorithms

• Words 3
• Finite State Algorithms
• Morphological Processing
• Sentences 3
• Parsing
• (Generation)
• Texts 3
• Tagging
• Chunking

13
Approach in this CoursePart II Topics and Tools

• Semantics 6
• Statistics 6
• Information Extraction 6
• Machine Translation 4
• Information Retrieval 3

14
Course Information

• Course Websitewww.cs.um.edu.mt/mros/csa3180
• Reference TextJurafsky and Martin
• Tools
• Prolog SWI Prolog
• NLTK nltk.sourceforge.net