Monday, August 30, 2010

Current Results & Presentation

I did a presentation last Friday on my current progress in the thesis, which can be found below.
Since then, I have managed to get Naive Bayes running in NLTK and it performs particularly well, almost in-line with SVM and above Maximum Entropy. I have been able to combine the three classifiers in a max-votes strategy, with the results:
weighted precision 66.74% modified precision 78.12%
weighted recall 67.29% modified recall 75.86%
weighted fscore 67.01% modified fscore 76.97%
Its important to remember that these (finalish) results are based on single annotations.
As I'm currently getting more annotations, I will update these with hopefully better performance
(but on a smaller subset of articles).


  1. Hi, Is the Australian Financial Review data set available for download. I am a researcher and would like to know the terms and conditions for the data set if available for download.


  2. Thanks for sharing this great article, I really enjoyed the insign you bring to the topic, awesome stuff!