Difference between revisions of "Munsee and English/Structural Transfer"
(→Structural Transfer Rules) |
(→Structural Transfer Rules) |
||
| Line 29: | Line 29: | ||
* Example Translation: (umu) '''nŭ'''moxoomsáya → (eng) '''my''' late grandfather | * Example Translation: (umu) '''nŭ'''moxoomsáya → (eng) '''my''' late grandfather | ||
| − | * Example Input: | + | * Example Input: moxóomus<n><aa>'''<px1sg>'''<abs> |
| − | * Example Output: | + | * Example Output: '''prpers<det><pos><p1><mf><sg>''' late<adj><sint> grandfather<n><sg> |
| Line 40: | Line 40: | ||
* Example Translation: (umu) nŭmoxooms'''áya''' → (eng) my '''late''' grandfather | * Example Translation: (umu) nŭmoxooms'''áya''' → (eng) my '''late''' grandfather | ||
| − | * Example Input: | + | * Example Input: moxóomus<n><aa><px1sg>'''<abs>''' |
| − | * Example Output: | + | * Example Output: prpers<det><pos><p1><mf><sg> '''late<adj><sint>''' grandfather<n><sg> |
== Post-Evaluation == | == Post-Evaluation == | ||
Latest revision as of 15:14, 6 May 2025
Pre-Evaluation
Statistics about input files
Number of words in reference: 35
Number of words in test: 14
Number of unknown words (marked with a star) in test: 10
Percentage of unknown words: 71.43 %
Results when removing unknown-word marks (stars)
Edit distance: 33
Word error rate (WER): 94.29 %
Number of position-independent correct words: 2
Position-independent word error rate (PER): 94.29 %
Structural Transfer Rules
Rule Description
Possessive Personal Pronouns
- Noun phrases in English get information about possession from nouns in Munsee
- Example Translation: (umu) nŭmoxoomsáya → (eng) my late grandfather
- Example Input: moxóomus<n><aa><px1sg><abs>
- Example Output: prpers<det><pos><p1><mf><sg> late<adj><sint> grandfather<n><sg>
Absence Suffix
- Noun phrases in English (noun w/ adjective "late") get information from nouns in Munsee (noun w/ absence suffix "aya").
- Example Translation: (umu) nŭmoxoomsáya → (eng) my late grandfather
- Example Input: moxóomus<n><aa><px1sg><abs>
- Example Output: prpers<det><pos><p1><mf><sg> late<adj><sint> grandfather<n><sg>
Post-Evaluation
Statistics about input files
Number of words in reference: 35
Number of words in test: 21
Number of unknown words (marked with a star) in test: 5
Percentage of unknown words: 23.81 %
Results when removing unknown-word marks (stars)
Edit distance: 24
Word error rate (WER): 68.57 %
Number of position-independent correct words: 11
Position-independent word error rate (PER): 68.57 %
