If anyone knows of a NLP-article using CRF (and explaining it's usage) please put a link to the article here (or mail it to Martin).
Subscribe to:
Post Comments (Atom)
This is the blog for the natural language processing reading group at the Copenhagen Business School. The reading group meets Thursdays in even weeks from 14-15 in room 2Ø.091 in Dalgas Have 15. The reading group is intended as a forum where researchers and their students can keep up-to-date on developments in natural language processing, and discuss books, papers, and software packages with state-of-the-art approaches to NLP.
At the last group meeting I mentioned that I had stumpled upon a PhD thesis using conditional random fields for word alignment. The thesis can be found here:
ReplyDeletehttp://www.clg.ox.ac.uk/blunsom/pubs/thesis.pdf
The author of the thesis (Phil Blunsom) also wrote a short article about the CRF word alignment:
http://acl.ldc.upenn.edu/P/P06/P06-1009.pdf
But I think that a better place to start is with an introduction to CRFs. For example:
http://www.cs.umass.edu/~mccallum/papers/crf-tutorial.pdf
which also demonstrates an application of CRFs in named entity recognition at the end. Although I haven't managed to get that far yet.
There is also an open source java implementation of CRFs to be found here:
http://crf.sourceforge.net/
Let's read the McCallum tutorial Andreas suggested for tomorrow, ie:
ReplyDeletehttp://www.cs.umass.edu/~mccallum/papers/crf-tutorial.pdf