Difference between revisions of "Ideas for Google Summer of Code/Improvements in lexical-selection module"
Jump to navigation
Jump to search
Line 7: | Line 7: | ||
* Do proper processing of tags in all scripts. |
* Do proper processing of tags in all scripts. |
||
* Remove unused and redundant scripts. |
* Remove unused and redundant scripts. |
||
+ | * Work on a way to trim non-significant features from the maximum-entropy models. |
||
* ''more here'' |
* ''more here'' |
||
Revision as of 21:04, 18 March 2013
Implement a number of optimisations to the lexical selection module. The lexical selection module in Apertium is currently a prototype. There are many optimisations that could be made to make it more efficient and faster, and easier to install and use.
Tasks
- Script/program for finding possibly missing bidix entries from an aligned parallel corpus.
- Do proper processing of tags in all scripts.
- Remove unused and redundant scripts.
- Work on a way to trim non-significant features from the maximum-entropy models.
- more here
Coding challenge
- Install Apertium and the constraint-based lexical selection module
- Run through the Generating lexical-selection rules from a parallel corpus HOWTO for a language pair of your choice.