This half unit course combines a critical introduction to key topics in theoretical and computational linguistics with hands-on practical experience of using existing software tools and developing applications to process texts and access linguistic resources.
The aims of the course and learning outcomes are listed in Chapter 1. This course has no specific prerequisites. There will be some programming involved and you will need to acquire some familiarity with the Python language, but you will not be expected to develop substantial original code or to encode specialised algorithms.
The course involves some statistical techniques, but the only mathematical knowledge assumed is an understanding of elementary probability and familiarity with the concept of logarithms. Before the advent of the world wide web, most machine-readable information was stored in structured databases and accessed via specialised query languages such as Structured Query Language (SQL). Nowadays the situation is reversed: most information is found in unstructured or semi-structured natural language documents and there is increasing demand for techniques to ‘unlock’ this data. Computing graduates with knowledge of natural language processing techniques are finding employment in areas such as text analytics, sentiment analysis, topic detection and information extraction.
Read More