Difference between revisions of "Lingala and Kikuyu/Structural Transfer"
From LING073
| Line 2: | Line 2: | ||
==Pre-Evaluation== | ==Pre-Evaluation== | ||
| + | Below are the evaluation statistics for both the mini test corpus and the full parallel corpus: | ||
| + | ===lin → kik evaluation=== | ||
| + | Evaluation of mini corpus: | ||
| + | * WER: 87.50% | ||
| + | * PER: 87.50% | ||
| + | * Percentage unknown words: 0.0% | ||
| + | * Percentage known words: 100% | ||
| + | |||
| + | Evaluation of full corpus: | ||
| + | * WER: 99.06% | ||
| + | * PER: 94.34% (unknown-word marks removed) | ||
| + | * Percentage unknown words: 66.67% | ||
| + | * Percentage known words: 33.33% | ||
| + | |||
| + | ===kik → lin evaluation=== | ||
| + | Evaluation of mini corpus: | ||
| + | * WER: 80.00% | ||
| + | * PER: 80.00% | ||
| + | * Percentage of unknown words: 0.0% | ||
| + | * Percents of known words: 100% | ||
| + | |||
| + | Evaluation of full corpus: | ||
| + | * WER: 98.13% | ||
| + | * PER: 90.65% (unknown-word marks remove) | ||
| + | * Percentage of unknown words: 70.75% | ||
| + | * Percentage of known words: 29.25% | ||
==Implementation== | ==Implementation== | ||
==Post-Evalatuion== | ==Post-Evalatuion== | ||
| + | ===lin → kik evaluation=== | ||
| + | Evaluation of mini corpus: | ||
| + | * WER: ? | ||
| + | * PER: ? | ||
| + | * Percentage unknown words: ? | ||
| + | * Percentage known words: ? | ||
| + | |||
| + | Evaluation of full corpus: | ||
| + | * WER: ? | ||
| + | * PER: ? (unknown-word marks removed) | ||
| + | * Percentage unknown words: ? | ||
| + | * Percentage known words: ? | ||
| + | |||
| + | ===kik → lin evaluation=== | ||
| + | Evaluation of mini corpus: | ||
| + | * WER: ? | ||
| + | * PER: ? | ||
| + | * Percentage of unknown words: ? | ||
| + | * Percents of known words: ? | ||
| + | |||
| + | Evaluation of full corpus: | ||
| + | * WER: ? | ||
| + | * PER: ? (unknown-word marks remove) | ||
| + | * Percentage of unknown words: ? | ||
| + | * Percentage of known words: ? | ||
[[Category:Sp17_StructuralTransfer]] | [[Category:Sp17_StructuralTransfer]] | ||
[[Category:Lingala]] | [[Category:Lingala]] | ||
[[Category:Kikuyu]] | [[Category:Kikuyu]] | ||
Revision as of 17:13, 2 April 2017
This page details transfer rules for translation between Lingala and Kikuyu
Contents
Pre-Evaluation
Below are the evaluation statistics for both the mini test corpus and the full parallel corpus:
lin → kik evaluation
Evaluation of mini corpus:
- WER: 87.50%
- PER: 87.50%
- Percentage unknown words: 0.0%
- Percentage known words: 100%
Evaluation of full corpus:
- WER: 99.06%
- PER: 94.34% (unknown-word marks removed)
- Percentage unknown words: 66.67%
- Percentage known words: 33.33%
kik → lin evaluation
Evaluation of mini corpus:
- WER: 80.00%
- PER: 80.00%
- Percentage of unknown words: 0.0%
- Percents of known words: 100%
Evaluation of full corpus:
- WER: 98.13%
- PER: 90.65% (unknown-word marks remove)
- Percentage of unknown words: 70.75%
- Percentage of known words: 29.25%
Implementation
Post-Evalatuion
lin → kik evaluation
Evaluation of mini corpus:
- WER: ?
- PER: ?
- Percentage unknown words: ?
- Percentage known words: ?
Evaluation of full corpus:
- WER: ?
- PER: ? (unknown-word marks removed)
- Percentage unknown words: ?
- Percentage known words: ?
kik → lin evaluation
Evaluation of mini corpus:
- WER: ?
- PER: ?
- Percentage of unknown words: ?
- Percents of known words: ?
Evaluation of full corpus:
- WER: ?
- PER: ? (unknown-word marks remove)
- Percentage of unknown words: ?
- Percentage of known words: ?