lasigeBioTM/MER

Issues

• The awk script does not work on Mac OS but works on Linux

  #40 opened 5 years ago by dpavot
  1

• Terms with punctuation

  #38 opened 5 years ago by AndreLamurias
  3

• Number of predictions drops for large requests

  #25 opened 7 years ago by AndreLamurias
  2

• awk error when annotating text with newlines

  #37 opened 8 years ago by LLCampos
  3

• Wrong index when more than one white space between words

  #12 opened 8 years ago by LLCampos
  1

• Genes file too big

  #29 opened 8 years ago by LLCampos
  1

• Wrong matching when period (.) is part of term

  #33 opened 8 years ago by LLCampos
  1

• Non-consistent behaviour "nicotinic acid"

  #35 opened 8 years ago by LLCampos
  0

• MER should work with all the most used awk interpreters?

  #34 opened 8 years ago by LLCampos
  0

• Matching term not existent in gazeeter

  #32 opened 8 years ago by LLCampos
  0

• List with entities repeated across vocabularies

  #27 opened 8 years ago by AndreLamurias
  4

• Incorrect field init (negative) in annotation

  #31 opened 8 years ago by AndreLamurias
  2

• Duplicated entities

  #30 opened 8 years ago by AndreLamurias
  0

• get_entities should match whole words only

  #28 opened 8 years ago by LLCampos
  4

• BeCalm Error when no entities are found

  #26 opened 8 years ago by AndreLamurias
  2

• There should be an option to do batch requests to external services

  #22 opened 8 years ago by LLCampos
  3

• Duplicate annotation when "—" is part of term

  #24 opened 8 years ago by LLCampos
  1

• Problem with the way get_entities.sh gets matches indexes

  #10 opened 8 years ago by LLCampos
  3

• Unicode characters in vocabularies don't match unicode characters in text

  #19 opened 8 years ago by LLCampos
  9

• get_entities should choose entity type according to the source used

  #23 opened 8 years ago by AndreLamurias
  2

• Isn't there something wrong with the scores?

  #20 opened 8 years ago by LLCampos
  2

• Entrez Direct bash library depends on Perl

  #21 opened 8 years ago by LLCampos
  0

• IBELight does not annotate entities that include words with less than three characters

  #4 opened 8 years ago by LLCampos
  1

• Second piped_pair_text has extra word

  #1 opened 8 years ago by LLCampos
  1

• Annotation offsets should be character offsets, not byte offsets

  #18 opened 8 years ago by LLCampos
  1

• Should annotate words between parenthesis

  #16 opened 8 years ago by LLCampos
  1

• Unicode Character 'EM SPACE' causes problems on annotations indexes

  #15 opened 8 years ago by LLCampos
  1

• Special characters are replaced by full stops in the output

  #17 opened 8 years ago by LLCampos
  0

• Different annotations in same document cannot overlap each other

  #9 opened 8 years ago by LLCampos
  1

• Missing annotation when word precedes a comma

  #13 opened 8 years ago by LLCampos
  0

• Index when "\xb5" and other symbol present in text to annotate.

  #14 opened 8 years ago by LLCampos
  0

• Wrong indexes

  #11 opened 8 years ago by LLCampos
  1

• get_entities.sh: line 60: /usr/bin/egrep: Argument list too long

  #8 opened 8 years ago by LLCampos
  1

• IBELight does not recognize terms with more than 2 words

  #3 opened 8 years ago by LLCampos
  1

• Change output to BeCalm TSV format

  #5 opened 8 years ago by LLCampos
  1

• Create script that evaluates IBELight against the BeCalm training corpus

  #6 opened 8 years ago by LLCampos
  1

• get_entities.sh should return nothing when does not find annotations

  #7 opened 8 years ago by LLCampos
  0

• Full stops should be ignored

  #2 opened 8 years ago by LLCampos
  1