Introduction to Natural Language Syntax and Parsing

Aims

This module aims to provide a brief introduction to linguistics for computer scientists and then goes on to cover some of the core tasks in natural language processing (NLP), focussing on statistical parsing of sentences to yield syntactic representations. We will look at how to evaluate parsers and see how well state-of-the-art tools perform given current techniques.

Syllabus

• Linguistics for NLP focusing on morphology and syntax
• Grammars and representations
• Statistical and neural parsing
• Treebanks and evaluation

Objectives

On completion of this module, students should:

• understand the basic properties of human languages and be familiar with descriptive and theoretical frameworks for handling these properties;
• understand the design of tools for NLP tasks such as parsing and be able to apply them to text and evaluate their performance;

Practical work

• Week 1-7: There will be non-assessed practical exercises between sessions and during sessions.
• Week 8: Download and apply two parsers to a designated text. Evaluate the performance of the tools quantitatively and qualitatively.

Assessment

• There will be one presentation worth 10% of the final mark; presentation topics will be allocated at the start of term.
• An assessed practical report of not more 8 pages in ACL conference format. It will contribute 90% of the final mark.

Recommended reading

Jurafsky, D. and Martin, J. (2008). Speech and Language Processing. Prentice-Hall (2nd ed.). (See also 3rd ed. available online.)