Domumentation of the Greenlandic analyser

What is this?

• Links to source code documentation.
• Source files: stems /   affixes /   twolc /   yaml
• Generation of:   paradigms /   text /

Here you find the technical documentation of the Greenlandic parser. The parser is built in close cooperation with the Sámi language technology project, with a file structure and setup close to the Sámi ones. General documentation can be found at the Sámi project documentation.

• The lexicon structure

In order to analyse Greenlandic text, you may paste in text in the window here. The machine returns text with all possible analyses. The tags are listed below. The parser gives tags for parts of speech, morphosyntactic categories, clitecs, and derivational tags. The derivational affixes have tags carrying the same names as the affixes themselves.

It is also possible to generate wordforms, by pasting the lemma and gramamtical tags here

In addition to giving all possible tags, the analyser also has a disambiguation mode, that gives only analyses appropriate in the given context.

The parser uses the following tags:

• Parts of speech: +N +V +Part +Pron +Adj +Adv +Prop +Interj +Num
• Morphosyntactic categories
  • Number:+Sg +Du +Pl
  • Case:+Abs +Rel +Trm +Abl +Lok +Aeq +Ins +Via
  • Mode:+Ind +Int +Imp +Opt +Cau +Con +Par +Inf +InfNeg +Ite
  • Person-number:+1Sg +2Sg +3Sg +4Sg +1Pl +2Pl +3Pl +4Pl +1Du
• Subcategories:+Attr +Abbr +ACR +Vok
• Clitics:+Clt
• Other:+Dato+
• Textual tags:+CLB +ABBR +PUNCT +LEFT +RIGHT
• Derivational tags: See the source code for a list.