Difference between revisions of "Corpus based preposition selection - HOWTO"
Jump to navigation
Jump to search
Fpetkovski (talk | contribs) |
Fpetkovski (talk | contribs) |
||
Line 7: | Line 7: | ||
* Use the trained model in the pipeline |
* Use the trained model in the pipeline |
||
− | The general toolkit for performing these tasks can be found here: |
+ | The general toolkit for performing these tasks can be found here: <br /> |
− | apertium.svn.sourceforge.net/svnroot/apertium/branches/gsoc2012/fpetkovski/morph-parser/ |
+ | [apertium.svn.sourceforge.net/svnroot/apertium/branches/gsoc2012/fpetkovski/morph-parser/ |
+ | ] |
||
− | |||
=== Extracting training data for your classifier === |
=== Extracting training data for your classifier === |
||
For the purpose of extracting training data for your classifier, you can use the preposition-extraction tool. |
For the purpose of extracting training data for your classifier, you can use the preposition-extraction tool. |
Revision as of 16:41, 20 August 2012
The general algorithm for performing corpus based preposition selection is as follows:
- Download a parallel corpus
- Extract patterns which contain prepositions from the source-language corpus
- Align the patterns to their translations in the target-language corpus
- Extract the features and label (the correct preposition from the target-language corpus) for classification.
- Train a model
- Use the trained model in the pipeline
The general toolkit for performing these tasks can be found here:
[apertium.svn.sourceforge.net/svnroot/apertium/branches/gsoc2012/fpetkovski/morph-parser/
]
Extracting training data for your classifier
For the purpose of extracting training data for your classifier, you can use the preposition-extraction tool.