Next: Comparative Architectures
Up: Lent Term 2000: Part
Previous: Security
Lecturer: Dr E.J. Briscoe
(ejb@cl.cam.ac.uk)
No. of lectures: 8
Prerequisite courses: none, but Regular Languages and Finite
Automata, Probability, Logic and Proof, and Artificial Intelligence
cover relevant material
Aims
This course aims to introduce the fundamental techniques of natural
language processing, to develop an understanding of the limits of
those techniques and of current research issues, and to evaluate some
current and potential applications.
- Introduction.
Brief history of NLP research, current applications, the
state-of-the-art, knowledge-based versus statistical
approaches.
- Morphology.
Inflection and derivation, finite-state morphology, ambiguity,
semi-productivity, part-of-speech disambiguation.
- Syntax.
Generative grammar, constituency, ambiguity, descriptive adequacy, a
simple unification-based grammar, where are NLs on the Chomsky
hierarchy?
- Parsing.
(Non-)deterministic parsing, parsing complexity, parsing
preferences (garden paths) and modularity, chart parsing.
- Semantics.
Truth-conditional semantics, compositionality, syntactically-driven
semantics, scope ambiguities, intensionality.
- Statistical parsing.
Coping with ambiguity and change/variation, probabilistic grammar,
grammar induction, lexical approaches and sparse data.
- Understanding (discourse).
Theorem proving, speech acts, reference, resolving anaphora,
discourse structure, abductive inference, and planning.
- Applications of NLP.
Database query, machine translation, information retrieval/extraction,
spoken language understanding, text-to-speech synthesis.
Objectives
At the end of the course students should
- be able to describe the architecture of and basic design for a
generic NLP system ``shell'' for a central task, such as mapping
text to appropriate logical representations
- be able to discuss the current and likely future performance of
several NLP applications, such as machine translation or
information retrieval
- be able to describe briefly a fundamental technique for
processing language for each of the main subtasks, such as
morphological analysis, syntactic parsing, etc (as indicated in the
lecture synopses)
- understand how these techniques draw on and relate to other
areas of (theoretical) computer science, such as formal language
theory, formal semantics of programming languages, or theorem
proving
- be able to compare and evaluate several approaches to some
subtasks, such as statistical versus knowledge-based part-of-speech
disambiguation or anaphora resolution
- recognise the major properties of natural languages and how
these relate to and differ from those of artificial languages
Recommended background reading
Pinker, S. (1994). The Language Instinct. Penguin.
Recommended books
Allen, J. (1987/1995). Natural Language
Understanding. Benjamin/Cummings (2nd ed. is the best single book on
NLP).
Russell, S. & Norvig, P. (1995). Artificial Intelligence: A
Modern Approach. Prentice-Hall. (Especially Chapter VII, but see
III, IV and V for supporting material.)
Next: Comparative Architectures
Up: Lent Term 2000: Part
Previous: Security
Christine Northeast
Mon Sep 20 10:28:43 BST 1999