Difference between revisions of "Apertium-kaz-tat/paper"
Jump to navigation
Jump to search
Firespeaker (talk | contribs) (→JNW) |
m |
||
(44 intermediate revisions by 3 users not shown) | |||
Line 1: | Line 1: | ||
− | + | Our paper was accepted to [http://www.mtsummit2013.info/impdates.asp MT Summit 2013]. You can read it [http://sourceforge.net/p/apertium/svn/HEAD/tree/trunk/apertium-kaz-tat/paper/ here]. |
|
− | == TODO == |
||
− | Ideal benchmarks: |
||
− | * document rules in the rlx with example sentences |
||
− | * more like 100-150 (currently ~40) disambiguation rules in -kaz |
||
− | |||
− | === Ilnar === |
||
− | * Development corpus (lots and lots of text) |
||
− | ** <s>Work on increasing coverage (via lexc) and trimmed coverage (via dix) to 90%</s> |
||
− | ** Work on making sure testvoc passes |
||
− | ** add rules — [[Apertium-kaz-tat/Ideas_for_Disambiguation_Rules|disambigation]] (CG), lexical selection, and transfer. |
||
− | * Test corpus (about 10 pages; don't base rules on this text!) |
||
− | ** Make a gold standard translation/correct some tests for [[Evaluation|error-rate testing]] |
||
− | * Paper |
||
− | ** <s>Add affiliation to paper</s> |
||
− | ** Help JNW come up with some more contrastive stuff (see below / <tt>FIXME: Ilnar</tt>s in paper) |
||
− | ** Find some exemplary bidix entries for figure 2. |
||
− | ** New example for table 3 (maybe Kazakh equivalent of original sentence) |
||
− | |||
− | === Fran === |
||
− | * Delegate out error-rate testing tasks |
||
− | * <s>new version of Table 2</s> |
||
− | |||
− | === JNW === |
||
− | * Work on last few issues in -tat twol |
||
− | * <s>Write up background</s> |
||
− | * Contrastive analysis of Kazakh and Tatar |
||
− | ** <s>phonological differences (a generalised summary, 2 or 3 small specific examples)</s> |
||
− | ** <s>orthographical differences (a generalised summary, 1 or 2 small specific examples)</s> |
||
− | ** <s>lexical and morphological differences (2 or 3 specific examples)</s> |
||
− | ** <s>morphotactic differences (2 or 3 specific examples)</s> |
||
− | ** syntactic differences (2 or 3 specific examples) |
||
− | * Coverage stuff |
||
− | ** divide corpora into 10 pieces and run coverage for each to get stddev |
||
− | |||
− | === Over-all === |
||
− | <s>1 2 3 3.1 3.2 3.3</s> 3.4 <s>4 4.1 4.2</s> 4.3 4.4 4.5 5 5.1 6 Acknowledgements <s>References</s> |
||
[[Category:Kazakh and Tatar|*]] |
[[Category:Kazakh and Tatar|*]] |
Latest revision as of 12:59, 16 March 2014
Our paper was accepted to MT Summit 2013. You can read it here.