Reading for Semester 2 week 2
Literature: Grammar based and statistical language models:
Core reading:
1. Jackendoff, R. (2002), Universal Grammar, Chapter 4 of Jackendoff, R.
Foundations of Language; Brain, Meaning, Grammar, Evolution, pages 68 – 78, Oxford University Press, 2002
Available from Edinburgh University Library
2. Wikipedia entry in Language Models, provides short summary, overview and references:
http://en.wikipedia.org/wiki/Language_model accessed 12th February 2010
3. This webside gives more insight into statistical language models. It explains the goals of a statistical language model and what they are used for in Computer Science. Focus your reading on the first 2 abstracts: "What is statistical language modellig(SLM)?" and "Common SLM techinques: N-gram model and variants". Author of this webpage and both abstracts is Le Zhang, PhD student at the School of Informatics, Edinburgh University. This webpage is still maintained by the author.
http://homepages.inf.ed.ac.uk/lzhang10/slm.html accessed 12th February 2010
Further reading
4. Lavrenko, V. and Croft, W. B. (2001) Relevance based language models, In
Proceedings of the 24th Annual international ACM SIGIR Conference on Research and Development in information Retrieval (New Orleans, Louisiana, United States). SIGIR ‘01. ACM, New York, NY, 120-127. PDF available online
5. Hockey, B. A. and Rayner, M. (2005)
Comparison of Grammar-Based and Statistical Language Models Trained on the Same Data, NASA Aimes Research Centre, American Association for Artificial Intelligence (www.aaai.org)
Available as:
http://ti.arc.nasa.gov/m/pub/1001h/1001%20(Hockey).pdf accessed 10th February 2010
6. Brown, M.K., Kellner, A. and Raggett, D. (2001)
Stochastic Language Models (N-Gram) Specification, W3C Working Draft 3 January 2001, Chapters 1 and 2
Available from:
http://www.w3.org/TR/ngram-spec/ accessed 10th February 2010
