Mchalfo1/Final Project

Paiwan Transducer

Work

Total Corpus: TOP UNKNOWN WORDS:

  1459 ^sa/*sa$
  1220 ^aicu/*aicu$
   863 ^ka/*ka$
   762 ^aza/*aza$
   596 ^avan/*avan$
   429 ^kemasi/*kemasi$
   423 ^mavan/*mavan$
   418 ^saka/*saka$
   394 ^uri/*uri$
   393 ^qaw/*qaw$
   376 ^azua/*azua$
   375 ^au/*au$
   329 ^uta/*uta$
   325 ^tucu/*tucu$
   285 ^maqati/*maqati$
   268 ^kai/*kai$
   265 ^masan/*masan$
   265 ^gu/*gu$
   252 ^pakata/*pakata$
   251 ^caviljan/*caviljan$

coverage: 70144 / 128503 (~0.54585496058457779196) remaining unknown forms: 58359 ambiguity: 136891 / 128503 (~1.06527474066753305370) pwn.longcorpus.txt Fri May 5 01:28:21 PM EDT 2023 70144/128503 ~0.54585496058457779196 \| 136891/128503 ~1.06527474066753305370 Wiki: TOP UNKNOWN WORDS:

  1429 ^sa/*sa$
  1207 ^aicu/*aicu$
   844 ^ka/*ka$
   762 ^aza/*aza$
   596 ^avan/*avan$
   419 ^kemasi/*kemasi$
   414 ^mavan/*mavan$
   406 ^saka/*saka$
   393 ^qaw/*qaw$
   375 ^au/*au$
   342 ^uri/*uri$
   310 ^uta/*uta$
   308 ^tucu/*tucu$
   274 ^maqati/*maqati$
   266 ^kai/*kai$
   265 ^gu/*gu$
   258 ^masan/*masan$
   252 ^pakata/*pakata$
   251 ^caviljan/*caviljan$
   247 ^sihu/*sihu$

coverage: 66909 / 122380 (~0.54673149207386827913) remaining unknown forms: 55471 ambiguity: 129818 / 122380 (~1.06077790488641934957) pwn.wiki20230501.txt Fri May 5 01:29:23 PM EDT 2023 66909/122380 ~0.54673149207386827913 \| 129818/122380 ~1.06077790488641934957

Genesis Chapters: OP UNKNOWN WORDS:

    31 ^uri/*uri$
    29 ^sa/*sa$
    29 ^azua/*azua$
    24 ^sun/*sun$
    24 ^marka/*marka$
    23 ^anga/*anga$
    17 ^su/*su$
    16 ^kadunangan/*kadunangan$
    14 ^vangal/*vangal$
    14 ^sika/*sika$
    14 ^qemati/*qemati$
    14 ^pai/*pai$
    14 ^ku/*ku$
    13 ^timadu/*timadu$
    13 ^qemuzimuzip/*qemuzimuzip$
    13 ^nimadu/*nimadu$
    13 ^nanguaq/*nanguaq$
    12 ^penulat/*penulat$
    12 ^keman/*keman$
    12 ^kacauan/*kacauan$

coverage: 1274 / 2441 (~0.52191724702990577632) remaining unknown forms: 1167 ambiguity: 2587 / 2441 (~1.05981155264235968865) pwn.bible Fri May 5 01:30:08 PM EDT 2023 1274/2441 ~0.52191724702990577632 \| 2587/2441 ~1.05981155264235968865

Developed Resources

• Paiwan Transducer: https://github.com/erchalfoun/ling073-pwn
• Spreadsheet of Paiwan words by dialect from Klokah: https://docs.google.com/spreadsheets/d/16waihA1bvzvOVU87oQg3XJUs-58o1DVCFpZX_W4odGY/edit?usp=sharing

External Resources

• Paiwan Textbook Ebooks: https://alilin.cip.gov.tw/tw/ebooks?tag=610&search_type=3&home_cat=0&button=&keyword=&cat=&zone=&city=0&area=