Difference between revisions of "Nuosu and Mandarin"
From LING073
(→Resources for machine translation between Nuosu and English) |
|||
| (19 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
| − | + | = Resources for machine translation between Nuosu and English = | |
| − | == | + | === Developed Resources === |
| − | *[https://github. | + | *[https://github.com/AgnesWang000/Nuosu-Mandarin-RBMT Nuosu-Mandarin Machine Translation Repository] |
| − | *[https://github. | + | *[https://github.com/AgnesWang000/Apertium-zho Mandarin(zho) Transducer Repository] |
| − | *[https://github. | + | *[https://github.com/AgnesWang000/Nuosu-Transducer Nuosu(iii) Transducer Repository] |
| − | *[https:// | + | *[https://wikis.swarthmore.edu/ling073/Nuosu_and_Mandarin/Contrastive_grammar Contrastive Grammar Documentation] |
| + | *[https://wikis.swarthmore.edu/ling073/Nuosu_and_Mandarin/Lexical_selection Lexical Selection Documentation] | ||
| + | *[https://wikis.swarthmore.edu/ling073/Nuosu_and_Mandarin/Structural_transfer Structural Transfer Documentation] | ||
| + | *[https://wikis.swarthmore.edu/ling073/Nuosu_and_Mandarin/Final_Project#Links_Public_Git_Repo_and_Poster Final Project: State-of-the-art MT and Transducer] | ||
| + | ==Polished RBMT System== | ||
| + | |||
| + | === Nuosu Transducer === | ||
| + | * Over : bible2.2022.1.31.txt (~249502 characters) | ||
| + | ** Precision: 97.6% | ||
| + | ** Recall: 86.46% | ||
| + | ** Coverage over large corpus: 75.43% | ||
| + | ** Stems in transducer: 300+ | ||
| + | |||
| + | === MT iii->zho === | ||
| + | * Over : iii.test.txt (30+ sentences) | ||
| + | ** Word Error Rate (WER): 38.6% | ||
| + | ** Position-independent word error rate (PER): 22.81% | ||
| + | ** Coverage: 78.5% | ||
== Additions == | == Additions == | ||
===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 18: | Line 37: | ||
* Added a rule which specified the explicit topic marker in Nuosu | * Added a rule which specified the explicit topic marker in Nuosu | ||
* Changed the rule that specified the organization of NP and ClP phrases | * Changed the rule that specified the organization of NP and ClP phrases | ||
| − | |||
===Adding Stems=== | ===Adding Stems=== | ||
* Added 100 new stems | * Added 100 new stems | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
[[Category: Nuosu]] [[Category: sp22_TranslationPairs]] | [[Category: Nuosu]] [[Category: sp22_TranslationPairs]] | ||
Latest revision as of 01:23, 13 May 2022
Contents
Resources for machine translation between Nuosu and English
Developed Resources
- Nuosu-Mandarin Machine Translation Repository
- Mandarin(zho) Transducer Repository
- Nuosu(iii) Transducer Repository
- Contrastive Grammar Documentation
- Lexical Selection Documentation
- Structural Transfer Documentation
- Final Project: State-of-the-art MT and Transducer
Polished RBMT System
Nuosu Transducer
- Over : bible2.2022.1.31.txt (~249502 characters)
- Precision: 97.6%
- Recall: 86.46%
- Coverage over large corpus: 75.43%
- Stems in transducer: 300+
MT iii->zho
- Over : iii.test.txt (30+ sentences)
- Word Error Rate (WER): 38.6%
- Position-independent word error rate (PER): 22.81%
- Coverage: 78.5%
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
Adding Stems
- Added 100 new stems
