I'm using cltk, a Python library for processing of classical languages.

I'm pos-tagging an example sentence, but I don't understand the output.

tagger.tag_unigram('Gallia est omnis divisa in partes tres')
# >>> [('Gallia', 'N-S---FB-'), ('est', 'V3SPIA---'), ('omnis', 'A-P---MA-'), ('divisa', 'T-SRPPFN-'), ('in', 'R--------'), ('partes', 'N-P---FA-'), ('tres', 'M--------')]

What does, for example 'N-S---FB-' mean?

From the docs of cltk.

  • 1
    Est is Verb 3rd.person Singular Feminine B, and I have no idea what B means; given the fact that est is an auxiliary verb and highly irregular, B may be some reference to grammatical phenomena. Btw, if you want a different parse of that sentence, try this.
    – jlawler
    Jul 11 '15 at 16:40
  • 1
    @jlawler 'B' surprisingly (in position 8) means Ablative. The full Key link in my answer.
    – Hugh
    Jul 13 '15 at 13:13

CLTK is producing parsing programs for classical Languages. Information on the LATIN version, including the copyright notice, can be found at kyle-p-johnson (notebooks):

Information is posted in a nine-letter string. Each position in the sequence signifies a category.

Nine string sequence:
.1. part of speech .2.person .3.number .4.tense .5.mood .6.voice .7.gender .8.case .9.degree. follow the traditional sequence for parsing a verb. The verb est is therefore described as v3spia ="verb.- 3rd person.-singular.- present.-indicative. -active."

Many of the codes will not be difficult to learn: person 1/2/3 ; number s/p (singular/plural) ; voice a/p (active/passive) gender m/f/n degree c/s (comparative/superlative) have larger sets, (e.g. B means 'ablative' vid.sup.) The m in .1. for tres indicates a numeral, but. m in .5. would indicate imperative. Full key.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.