direct-phonology/jdsw

Issues

• add a streamlit interface for testing span categorization

  #48 opened 9 months ago by thatbudakguy
  0

• Detect and label restatements of the headword

  #56 opened 10 months ago by thatbudakguy
  1

• Add an algorithm for inferring relations between spans

  #61 opened a year ago by thatbudakguy
  1

• find named entities in annotations

  #35 opened a year ago by thatbudakguy
  2

• Separate relation and span annotation

  #55 opened a year ago by thatbudakguy
  0

• Add project task to export annotations

  #54 opened a year ago by thatbudakguy
  0

• add a streamlit interface for testing named entity predictions

  #46 opened a year ago by thatbudakguy
  1

• train a span categorizer on jeff & hantao's data

  #45 opened a year ago by thatbudakguy
  2

• handle "all below/above" annotations

  #4 opened 2 years ago by thatbudakguy
  2

• rearrange POS tags in priority order

  #43 opened a year ago by thatbudakguy
  1

• use SuPaR-Kanbun as the base model

  #36 opened 2 years ago by thatbudakguy
  0

• source/commentary alignment detection is incorrect

  #18 opened 2 years ago by thatbudakguy
  7

• add logging

  #27 opened 2 years ago by thatbudakguy
  1

• add visualization

  #29 opened 2 years ago by thatbudakguy
  1

• check to see whether NER patterns occur in annotation corpus

  #39 opened 2 years ago by thatbudakguy
  1

• parse annotations using a model

  #32 opened 2 years ago by thatbudakguy
  2

• run topic modeling algorithm on annotations

  #31 opened 2 years ago by thatbudakguy
  1

• restructure as spaCy project

  #34 opened 2 years ago by thatbudakguy
  0

• update README

  #21 opened 2 years ago by thatbudakguy
  0

• fix missing pages in SBCK edition of the JDSW

  #28 opened 2 years ago by thatbudakguy
  0

• implement pipeline pattern for data transformations

  #22 opened 2 years ago by thatbudakguy
  1

• convert bulk processing scripts to use fileinput

  #19 opened 2 years ago by thatbudakguy
  1

• automatically align jdsw with cleaned source texts

  #11 opened 2 years ago by thatbudakguy
  6

• generate CoNLL-U base versions of all texts

  #23 opened 2 years ago by thatbudakguy
  0

• add zhengwen versions of missing texts

  #9 opened 2 years ago by thatbudakguy
  3

• output list of variant readings occuring in JDSW but not attested in SBGY

  #16 opened 2 years ago by GDRom
  3

• better handling for cases of multiple readings

  #17 opened 2 years ago by thatbudakguy
  1

• implement conversion from middle chinese to old chinese

  #3 opened 2 years ago by thatbudakguy
  3

• fix missing pages in the jdsw

  #14 opened 2 years ago by thatbudakguy
  3

• add sbck versions of missing texts

  #12 opened 2 years ago by thatbudakguy
  0

• segment sentences and number tokens in output

  #8 opened 2 years ago by thatbudakguy
  1

• clean annotations of commentaries from jdsw

  #10 opened 2 years ago by thatbudakguy
  0

• shift output representation to separate initials, finals, and tones

  #6 opened 2 years ago by thatbudakguy
  0

• handle character variants when loading data

  #7 opened 2 years ago by thatbudakguy
  1

• Port scripts from och-g2p

  #1 opened 2 years ago by thatbudakguy
  0

• handle lookups for variant characters

  #5 opened 2 years ago by thatbudakguy
  1

• correct readings generated by fanqie annotations

  #2 opened 2 years ago by thatbudakguy
  1