Course pages 2014–15
Overview of Natural Language Processing
Assessment is by coursework as follows:A practical is performed where a corpus of texts is given, and students write code that detects the sentiment of each text as positive or negative. Various natural language processing tools will be tested as to how they improve performance on the task.
The corpus is available at /usr/groups/mphil/L90. You can also find
additional resources there in the "resources" directory, e.g., material on how to perform a sign
test (description from Siegel and Castellan (1986) "Nonparametric Statistics for the Behavioral Sciences" is also available here), and instructions on how to write the report.
Please also read the following instructions for Preparation.
Practical class 1 (Nov 14, 9.00-11.00): Sentiment and effects
of POS
Practical class 2 (Nov 28, 9.00-11.00): Sentiment and effects
of parsing/higher-level processing
Assessment is by a report on the practical of no more than 4000 words,
which needs to be submitted by the deadline of Wednesday January 14 by
12.00noon.