Module 06-02495 (2011)

• introduce Natural Language Processing as one of the components of Artificial Intelligence, both from engineering and cognitive viewpoints
• show how Natural Language Processing techniques can be programmed using the Prolog programming language

• describe major trends and systems in Natural Language Processing
• define: morphology; syntax; semantics; pragmatics; and give appropriate examples to illustrate their definitions
• describe several standard methods of applying morphological and syntactic knowledge in Natural Language Processing systems, for instance: finite-state methods; probabilistic methods; context-free grammars and parsers, including the Active Chart Parsers; unification grammars and parsing
• implement context-free grammars implemented by Prolog's Definite Clause Grammar
• describe simple feature-based semantic systems typically based on logic showing the difference between building semantic representations and interpreting semantic representations
• demonstrate a knowledge of two or more methods for resolving pronoun referents as an example of semantic interpretation
• show an understanding of the role of pragmatics in understanding natural language
• describe an application of natural language processing (for instance machine translation) and show the place of syntactic, semantic and pragmatic processing

2 hrs/week lectures and exercise classes.

• Sessional: 1.5 hr examination (50%), continuous assessment (50%).
• Supplementary: By examination only.

1. Introduction and Overview (1 week)
2. Finite State Networks & Transducers (1 week)
3. Simple grammars (1 week)
4. Basic parsing algorithms (1 week)
5. Active chart parsing (1 week)
6. Features (1 week)
7. Semantics (1 week)
8. Discourse Representation Theory (1 week)
9. Discourse (1 week)
   • Cohesion in Text
   • Pronoun Reference Resolution
10. Pragmatics (1 week)
    • Speech Acts
    • Pragmatic Inference
11. Applications (1 week)