Natural Language Processing

Lecturer: Dr A.A. Copestake (aac10@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

This course is a prerequisite for Information Retrieval.

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.

Lectures

• Introduction. Brief history of NLP research, current applications, NLP system architecture, knowledge-based versus probabilistic approaches.

• Finite-state techniques. Inflectional and derivational morphology, finite-state automata in NLP, finite-state transducers.

• Prediction and part-of-speech tagging. Corpora, simple N-grams, word prediction, stochastic tagging, evaluating system performance.

• Parsing and generation I. Generative grammar, context-free grammars, parsing and generation with context-free grammars, weights and probabilities.

• Parsing and generation II. Constraint-based grammar, unification, simple compositional semantics, interfacing to knowledge bases.

• Lexical semantics. Semantic relations, WordNet, word senses, word sense disambiguation.

• Discourse and dialogue. Discourse relations, anaphora resolution, dialogue modelling.

• Applications. Machine translation, email response, spoken dialogue systems.

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''

• be able to discuss the current and likely future performance of several NLP applications, such as machine translation and email response

• be able to describe briefly a fundamental technique for processing language for several subtasks, such as morphological analysis, parsing, word sense disambiguation etc.

• 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

Recommended book

Jurafsky, D. & Martin, J. (2000). Speech and Language Processing. Prentice-Hall.