COMP348: Document Processing and the Semantic Web
Resources and Support Materials : COMP348
The textbook of the unit is:
- Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit, by Steven Bird, Ewan Klein, and Edward Loper. This book is published by O'Reilly, but there's also a freely available online version here.
Other readings will be assigned week-by-week in class. These will always either be available in the library, or online.
The following books provide additional information on topics covered during the course, and are either in the library (call numbers are in parentheses) or online via the link provided:
- Jurafsky and Martin. Speech and Language Processing, Upper Saddle River, NJ ; Prentice Hall, 2009. xxxi, 999p. ISBN: 0131873210. (Call no. P98 .J87 2009)
- Manning, Raghavan and Schütze. Introduction to Information Retrieval. Cambridge University Press, 2008. ISBN: 0521865719. You can download the book in PDF format.
- Jackson and Moulinier, Natural Language Processing for Online Applications, John Benjamins, ISBN: (Call no. QA76.9.N38 J33 2002)
- Manning and Schütze. Foundations of Statistical Natural Language Processing, Cambridge, MA ; MIT Press, 1999. xxxvii, 680p. ISBN: 0-262-13360-1. (Call no. P98.5.S83.M36/1999)
Each week, you will be assigned some reading for the unit. This is obligatory: you will not understand the lectures if you do not keep up with the reading, and you will not be able to do the practical exercises if you do not do the reading.
You will also need to access materials on programming in Python. If you want to get a book, look at the list of Python books at python.org. Other online resources are mentioned below.
Below is a list of online resources for the unit. The contents will change as the course progresses. If you find any broken links, let us know. Watch this space!
- The python.org tutorial
- Dive Into Python is a free book for experienced programmers.
- Python Sorting Mini-Howto is a good tutorial on how to sort lists in various ways.
- Python Regular Expression Howto will tell you all you need to know about REs
Python: Conventions and Static Typing
- PEP 8, a coding standard available at python.org
- PyChecker, a static analysis tool
- An opinion on static typing vs dynamic typing + automated testing
- Another opinion