Eastern Burushaski and English/Structural transfer

From LING073
Revision as of 19:41, 16 April 2019 by Cwillia7 (talk | contribs) (things implemented)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

before

Test file: 'bsk-eng.tests.txt' Reference file 'eng.tests.txt'

Statistics about input files


Number of words in reference: 50 Number of words in test: 40 Number of unknown words (marked with a star) in test: Percentage of unknown words: 0.00 %

Results when removing unknown-word marks (stars)


Edit distance: 49 Word error rate (WER): 98.00 % Number of position-independent correct words: 2 Position-independent word error rate (PER): 96.00 %

Results when unknown-word marks (stars) are not removed


Edit distance: 49 Word Error Rate (WER): 98.00 % Number of position-independent correct words: 2 Position-independent word error rate (PER): 96.00 %

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%

things implemented

  • sentence: aa ine gane t̪ayaar baa
  • "I am ready for him"

We implemented copulas and postpositions. Both of these are exhibited in this example sentence.

tagger

^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for<pr>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<vbser><pres><ind><p1><sg>$

biltrans

^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for<pr>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<vbser><pres><ind><p1><sg>$


chunker

apertium-transfer: Rule 3 e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>

apertium-transfer: Rule 3 in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>

apertium-transfer: Rule 1 gane<post>/for<pr>

apertium-transfer: Rule 2 t̪ayaar<n>/ready<n>

apertium-transfer: Rule 5 b<cop><pres><ind><p1><sg>/be<vbser><pres><ind><p1><sg> ^prn<NOUN>{^I<prn><pers><p1><sg><abs>$}$ ^prn<NOUN>{^that<dem><dst><sg><mf>$}$ ^prep<POST>{^for<pr>$}$ ^noun<NOUN>{^ready<n>$}$ ^cop<SV><pres><p1><sg>{^be<vbser><2><3><4>$}$


interchunk

apertium-interchunk: Rule 3 prn<NOUN>{^that<dem><dst><sg><mf>$} prep<POST>{^for<pr>$}

apertium-interchunk: Rule 2 cop<SV><pres><p1><sg>{^be<vbser><2><3><4>$} ^prn<NOUN>{^I<prn><pers><p1><sg><abs>$}$ ^prep<POST>{^for<pr>$}$ ^prn<NOUN>{^that<dem><dst><sg><mf>$}$ ^noun<NOUN>{^ready<n>$}$ ^cop<SV><pres><p1><sg>{^be<vbser><2><3><4>$}$

postchunk

^I<prn><pers><p1><sg><abs>$ ^for<pr>$ ^that<dem><dst><sg><mf>$ ^ready<n>$ ^be<vbser><pres><p1><sg>$


bsk-eng (full translation)

#I for #that #ready am

after

Statistics about input files


Number of words in reference: 40 Number of words in test: 40 Number of unknown words (marked with a star) in test: Percentage of unknown words: 0.00 %

Results when removing unknown-word marks (stars)


Edit distance: 40 Word error rate (WER): 100.00 % Number of position-independent correct words: 0 Position-independent word error rate (PER): 100.00 %

Results when unknown-word marks (stars) are not removed


Edit distance: 40 Word Error Rate (WER): 100.00 % Number of position-independent correct words: 0 Position-independent word error rate (PER): 100.00 %

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%