Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

The SPECIALIST Lexicon

Antonym Generation for SD Model

shell>cd ${ANTONYM_DIR}/bin
shell>GetAntonyms ${YEAR}

SD model: Suffix Derivations with Negations
Use the latest SuffixD (derivation.data.${YEAR}) and inflVars.data

OptionDescriptioninputOutputNotesOption
20
  • Get antonym candidates from SuffixD
  • Derivation.GetAntCandFromSuffixD.java
  • ${SD_DIR}/input/derivation.data (add link)
  • ${LEX_DIR}/input/inflVars.data
  • ${ANT_DIR}/input/antCand.data.tag.${YEAR}
  • ${ANT_DIR}/input/domain.data
  • ./output/Cand/antCandSuffixD.data
  • ./output/Cand/antCandSuffixD.data.tag
    => aPairs alreayd tagged
  • ${SD_DIR}/output/Cand/antCandSuffixD.data.tbd
    => aPairs to be tagged, send to linguists, need to be 0
  • ./output/candTagged/antCandSuffixD.data.tag.tagged
  • If the first time:
    • mkdir ./${YEAR}/output/Cand
    • mkdir ./${YEAR}/output/candTagged
  • Use updated derivation.data and inflVars.data
  • Send antCandSuffixD.data.tbd to linguist to complete the tags
  • Complete Steps 21-22, then re-run this step until TBD = 0
20
21
  • Validate and fix tags of antonym candidates (SD)
  • Antonym.ValidateTaggedCand.java
  • ./output/candTagged/antCandSuffixD.data.tag.tagged
  • ${ANT_DIR}/input/domain.data
  • ./output/candTagged/antCandSuffixD.data.tag.fixed
  • Append linguist's tags to ${SD_DIR}/output/candTagged/antCandSuffixD.data.tag.tagged
  • Run this step until the tag and fixed files are the same
    • Fixed file is the auto-fixes on [TYPE_TBD] and [DOMAIN_TBD] to [NA] and [DOMAIN_NONE].
    • Fixed file is sorted by alphabetical order.
    • Manually copy the fixed file to tagged file
  • Manually copy antCandSuffixD.data.tag.tagged to antCandSuffixD.data.tag.tagged.${YEAR}
  • Go to Step-22
  • Need to rerun this step after Step 20 has TBD=0, so the fixed file is sorted alphabetically
21
22
  • Update release antonyms tagged file form SD
  • Antonym.UpdateAllTaggedFile.java
  • ./output/candTagged/antCandSuffixD.data.tag.tagged.${YEAR} (copy from antCandSuffixD.data.tag.tagged)
  • ${ANT_DIR}/input/antCand.data.tag.${YEAR}
  • ${ANT_DIR}/input/domain.data
  • ${ANT_DIR}/input/antCand.data.tag.updated
  • The step automatically updates all antonym candidate tag file
  • In ${ANT_DIR}/input/, Manually copy antCand.data.tag.updated to antCand.data.tag.updated.2.SD
  • In ${ANT_DIR}/input/, Manually copy antCand.data.tag.updated to antCand.data.tag.${YEAR}
  • The output file is used to generate antonym and negation files for the release.
  • Re-run steps 20-22 until it passes all steps (follow instruction in log).
    • tag conflict no = 0
    • source conflict no = 0
    • duplicate tag = 0
22