Tiwi and English/Structural transfer
Contents
Pre-Evaluation
Statistics about input files
Number of words in reference: 41
Number of words in test: 28
Number of unknown words (marked with a star) in test: 13
Percentage of unknown words: 14.63%
Results when removing unknown-word marks (stars)
Edit distance: 36
Word error rate (WER): 87.8%
Number of position-independent correct words: 5
Position-independent word error rate (PER): 87.8%
Results when unknown-word marks (stars) are not removed
Edit distance: 36
Word error rate (WER): 87.8%
Number of position-independent correct words: 5
Position-independent word error rate (PER): 87.8%
Statistics about the translation of unknown words
Number of unknown words which were free rides: 0
Percentage of unknown words that were free rides: 0%
Examples
Add at least one example sentence for each item you implement. Show the outputs of the following modes for your translation system: tagger, biltrans, transfer, and the pair itself (abc-xyz).
Gendered Nouns and Adjectives
Eng-Tiw
(tiw) ngarra kijinga → (eng) he is small
Tagger
(tiw) ngarra<prn><pers><p3><m><sg> kiji<adj><f> → (eng) prpers<prn><subj><p3><m><sg> be<vbser><pres><p3><sg> small <adj><sint>
Biltrans
^ngarra<prn><m><p3><sg>/he<prn><m><p3><sg>$ ^kiji<adj><f>/small<adj><sint><f>$^.<sent>/.<sent>$
Transfer
"ngarra kijinga" → ^he<prn><p3><m><sg>$ ^be<vbser><pres><p3><sg>$ ^small<adj><sint>$^.<sent>$
Post Evaluation
Statistics about input files
Number of words in reference:
Number of words in test:
Number of unknown words (marked with a star) in test:
Percentage of unknown words:
Results when removing unknown-word marks (stars)
Edit distance:
Word error rate (WER):
Number of position-independent correct words:
Position-independent word error rate (PER):
Results when unknown-word marks (stars) are not removed
Edit distance:
Word Error Rate (WER):
Number of position-independent correct words:
Position-independent word error rate (PER):
Statistics about the translation of unknown words
Number of unknown words which were free rides:
Percentage of unknown words that were free rides: