Difference between revisions of "LakotaandEnglish"

From LING073
Jump to: navigation, search
(→‎Additions)
Line 39: Line 39:
  
 
= Additions =  
 
= Additions =  
−
* At least 4 more twol rules that make your (analysis and) generation cleaner for an additional way.
+
* Expand your morphology to cover at least 5 more elements of some paradigm(s). This can be anything from additional verb or noun morphology, to adding all the forms of all the determiners (articles, demonstratives, etc.), to implementing nominal morphology on adjectives (e.g., if your language allows adjectives to be substantivised, which you'll want to add a tag for too).
 
* At least 3 new disambiguation rules that make the output of your tagger more accurate.
 
* At least 3 new disambiguation rules that make the output of your tagger more accurate.
 
* At least 2 new transfer rules that make more of the output of your MT system closer to an acceptable target translation.
 
* At least 2 new transfer rules that make more of the output of your MT system closer to an acceptable target translation.

Revision as of 23:45, 5 May 2022

Resources for machine translation between Lakota and English

External resources

lkt -> eng Evaluation

Coverage on Monolingual Transducer :

Coverage on Bilingual Transducer :

Our Ten Analyzed Sentences

The original sentence, The intended English translation, The output of your xyz-abc-biltrans (lexical transfer) mode, The output of your xyz-abc (full translation) mode.

1)

2)

3)

4)

5)

6)

7)

8)

9)

10)

Additions

  • Expand your morphology to cover at least 5 more elements of some paradigm(s). This can be anything from additional verb or noun morphology, to adding all the forms of all the determiners (articles, demonstratives, etc.), to implementing nominal morphology on adjectives (e.g., if your language allows adjectives to be substantivised, which you'll want to add a tag for too).
  • At least 3 new disambiguation rules that make the output of your tagger more accurate.
  • At least 2 new transfer rules that make more of the output of your MT system closer to an acceptable target translation.

Final Evaluation