0

I've got a training DataSet and a Test DataSet. How can we experiment and get results ? Can WEKA be used for the same ?

The topic is Word Sense Disambiguation using Support Vector Machine Supervised learning Approach

The Document types within both the sets include following file types: 1. 2 XML files 2. README file 3. SENSEMAP format 4. TRAIN format 5. KEY format 6. WORDS format

Krithi07
  • 481
  • 2
  • 7
  • 18

1 Answers1

2

Machine learning approaches like SVM are not popular with word sense disambiguation.
Are you aware of Wikify, mapping to wikipedia can be considered very fine word-sense disambiguation.
To answer your question, in cases like these; any machine learning technique can give you desired results. One should be more worried about the features to extract and make sure the word features are distinctive enough to resolve the disambiguations at the level you chose. For example in the sentence: Wish you a very Happy Christamas you just want to disambiguate Happy Christmas as either book or festival.

Vihari Piratla
  • 8,308
  • 4
  • 20
  • 26
  • From the various papers that I refereed, it turns out that SVM is one of the best methods for word sense disambiguation. – Krithi07 Nov 11 '14 at 19:34
  • I wanted to know if its possible to evaluate a test set if I have a training set by using either of WEKA or R ? – Krithi07 Nov 11 '14 at 19:34
  • What do you mean evaluate your test set? What is your test set(any link?) anyway I have never used WEKA before. – Vihari Piratla Nov 11 '14 at 19:39
  • Okay if not WEKA, R ? Senseval-3 EnglishLS is what I'm taking as training and test datasets – Krithi07 Nov 11 '14 at 19:43