Difference between revisions of "Sardinian and English/Structural transfer"
From LING073
(→pre-evaluation) |
(→pre-evaluation) |
||
| Line 20: | Line 20: | ||
1 Lettu | 1 Lettu | ||
*coverage from bilingual transducer on srd.tests: | *coverage from bilingual transducer on srd.tests: | ||
| + | Number of tokenised words in the corpus: 91 | ||
| + | Coverage: 84.62% | ||
| + | Top unknown words in the corpus: | ||
| + | 2 bellu | ||
| + | 1 paisu | ||
| + | 1 paìsu | ||
| + | 1 Lettu | ||
| + | 1 furatu | ||
| + | 1 dinari | ||
| + | 1 punitos | ||
| + | 1 rica | ||
| + | 1 datu | ||
| + | 1 milli | ||
| + | 1 francos | ||
| + | 1 betzu | ||
| + | 1 iscimpru | ||
[[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]] | [[Category:Sp23_StructuralTransfer]],[[Category:Sardinian]],[[Category:English]] | ||
Revision as of 17:11, 2 May 2023
pre-evaluation
- WER, PER, and other useful numbers:
Statistics about input files ------------------------------------------------------- Number of words in reference: 81 Number of words in test: 80 Number of unknown words (marked with a star) in test: 14 Percentage of unknown words: 17.50 %
Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 77 Word error rate (WER): 95.06 % Number of position-independent correct words: 12 Position-independent word error rate (PER): 85.19 %
- coverage from monolingual transducer on srd.tests:
Coverage: 97.78% Top unknown words in the corpus: 1 paìsu 1 Lettu
- coverage from bilingual transducer on srd.tests:
Number of tokenised words in the corpus: 91 Coverage: 84.62% Top unknown words in the corpus: 2 bellu 1 paisu 1 paìsu 1 Lettu 1 furatu 1 dinari 1 punitos 1 rica 1 datu 1 milli 1 francos 1 betzu 1 iscimpru,,