Difference between revisions of "Nuosu and Mandarin"
From LING073
(→Polished RBMT System) |
(→Additions) |
||
| Line 11: | Line 11: | ||
===Disambiguation=== | ===Disambiguation=== | ||
| − | * Added a | + | * Added a rule that distinguishes adverbs and main verbs (ex. ꃅ) |
| + | * Added a rule that distinguishes exhaustion particles and main verbs for (ex. ꌐ) | ||
| + | * Added a rule that distinguishes end-of-sentence particles and main verbs for (ex. ꄉ) | ||
| + | |||
===Structural Transfer=== | ===Structural Transfer=== | ||
| Line 22: | Line 25: | ||
===Adding Stems=== | ===Adding Stems=== | ||
* Added 100 new stems | * Added 100 new stems | ||
| − | |||
==Polished RBMT System== | ==Polished RBMT System== | ||
Revision as of 20:00, 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 rule that distinguishes adverbs and main verbs (ex. ꃅ)
- Added a rule that distinguishes exhaustion particles and main verbs for (ex. ꌐ)
- Added a rule that distinguishes end-of-sentence particles and main verbs for (ex. ꄉ)
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: 182179 / 243953 (~0.74677909269408451628) remaining unknown forms: 61774
- Stems in transducer: 276
- Over : #small corpus
- Word Error Rate (WER): %
- Position-independent word error rate (PER): %
- Percentage of unknown words: %
- Number of position-independent correct words:
- Coverage:
- Over
- Coverage:
