Difference between revisions of "Nuosu and Mandarin"
From LING073
(Created page with "== Resources for machine translation between Nuosu and English == == External Resources == *[https://github.swarthmore.edu/Ling073-sp22/ling073-iii-zho Nuosu-Mandarin Machin...") |
|||
Line 8: | Line 8: | ||
+ | == Additions == | ||
+ | ===Disambiguation=== | ||
+ | * Added a disambiguation rule...twol rule | ||
+ | |||
+ | ===Structural Transfer=== | ||
+ | * Added one more sentence for each of the five rules, bringing the total to 10 sentences | ||
+ | * Added a rule which added an adjective-specific marker when translating to Mandarin. | ||
+ | * Added a rule which specified the explicit topic marker in Nuosu | ||
+ | * Changed the rule that specified the organization of NP and ClP phrases | ||
+ | * These changes brought our WER from xxxx% to xx% | ||
+ | |||
+ | ===Adding Stems=== | ||
+ | * Added 100 new stems | ||
+ | |||
+ | |||
+ | ==Polished RBMT System== | ||
+ | * Precision: % | ||
+ | * Recall: % | ||
+ | * Coverage over large corpus: | ||
+ | * Stems in transducer: | ||
+ | * Over : | ||
+ | ** Word Error Rate (WER): % | ||
+ | ** Position-independent word error rate (PER): % | ||
+ | ** Percentage of unknown words: % | ||
+ | ** Number of position-independent correct words: | ||
+ | ** Coverage: | ||
+ | * Over | ||
+ | ** Coverage: | ||
Revision as of 14:57, 1 May 2022
Contents
Resources for machine translation between Nuosu and English
External Resources
- Nuosu-Mandarin Machine Translation Repository
- Mandarin(zho) Transducer
- Nuosu(iii) Transducer
- iii-zho corpus repository
Additions
Disambiguation
- Added a disambiguation rule...twol rule
Structural Transfer
- Added one more sentence for each of the five rules, bringing the total to 10 sentences
- Added a rule which added an adjective-specific marker when translating to Mandarin.
- Added a rule which specified the explicit topic marker in Nuosu
- Changed the rule that specified the organization of NP and ClP phrases
- These changes brought our WER from xxxx% to xx%
Adding Stems
- Added 100 new stems
Polished RBMT System
- Precision: %
- Recall: %
- Coverage over large corpus:
- Stems in transducer:
- Over :
- Word Error Rate (WER): %
- Position-independent word error rate (PER): %
- Percentage of unknown words: %
- Number of position-independent correct words:
- Coverage:
- Over
- Coverage: