Difference between revisions of "Guarani/Transducer"
From LING073
(→Evaluation) |
(→Evaluation) |
||
| Line 23: | Line 23: | ||
|- | |- | ||
|''i'' | |''i'' | ||
| − | |||
| − | |||
|25 | |25 | ||
|- | |- | ||
Revision as of 01:21, 17 February 2017
Transducer for Guarani (Work in progress).
Evaluation
The current corpus coverage is 2.85% (out of 1016 tokenized words in the corpus).
The most missed words were:
| Word | Occurences |
|---|---|
| ha | 44 |
| a | 43 |
| va | 41 |
| pe | 27 |
| i | 25 |
| e | 20 |
| m | 18 |
| ra | 17 |
| ta | 10 |
| o | 10 |
| guarani | 9 |
| up | 9 |
| ñe | 9 |
| yvy | 9 |
| y | 9 |
| icha | 9 |
| me | 8 |
| rã | 7 |
| Tupã | 7 |
| t | 7 |
Notes
Links
The transducer is available on Github.
