Difference between revisions of "Generating lexical-selection rules from a parallel corpus"
Jump to navigation
Jump to search
(Created page with 'If you have a parallel corpus, one of the things you can do is generate some lexical selection rules from it, to improve translation of words with more than one possible translat…') |
|||
Line 7: | Line 7: | ||
* Giza++ (or some other word aligner) |
* Giza++ (or some other word aligner) |
||
* Moses (for making Giza++ less human hostile) |
* Moses (for making Giza++ less human hostile) |
||
+ | * All the Moses scripts |
||
* lttoolbox |
* lttoolbox |
||
* Apertium |
* Apertium |
||
Line 15: | Line 16: | ||
* an Apertium language pair |
* an Apertium language pair |
||
* a parallel corpus |
* a parallel corpus |
||
− | |||
== Getting started == |
== Getting started == |
||
+ | |||
Revision as of 11:36, 17 January 2012
If you have a parallel corpus, one of the things you can do is generate some lexical selection rules from it, to improve translation of words with more than one possible translation.
You will need
Here is a list of software that you will need installed:
- Giza++ (or some other word aligner)
- Moses (for making Giza++ less human hostile)
- All the Moses scripts
- lttoolbox
- Apertium
- apertium-lex-tools
Furthermore you'll need:
- an Apertium language pair
- a parallel corpus