Apertium-aze

From Apertium
Jump to navigation Jump to search

Azmorph, a morphological analyzer for Azerbaijani

Azmorph current version is 0.2.1 (preALPHA)

What it is, what it does and what it does not[edit]

Azmorph is a morphological analyzer for Azerbaijani (Azerbaycan dili).

Due to the similarities between Azerbaijani and Turkish Azmorph is being developed starting from TRmorph of Çağrı Çöltekin.

Azmorph is at preALPHA stage of developement: this means that it works for very few features of the language (which will be explained later). If you are not familiar with the nerdish jargon, preALPHA means roughly that the software is in its embryonal state. Is it already a life? We don't know, better you consult your local Church. What we know is that, beside being a problematic embryo we decided to keep it and try to provide it with a decent development. We know it will be a problematic child, probably with several impairments, but we decided to keep it anyway.

Current State[edit]

{{#set_param_default | corpus1 | None }} {{#set_param_default | corpus2 | None }} {{#set_param_default | corpus3 | None }} {{#set_param_default | corpus4 | None }} {{#set_param_default | corpus5 | None }} {{#set_param_default | corpus6 | None }} {{#set_param_default | corpus7 | None }} {{#set_param_default | corpus8 | None }} {{#set_param_default | corpus9 | None }} {{#set_param_default | corpus10 | None }}

{{#ifneq | azadliq2012 | None |

{{#ifneq | RFERL corpora | | | }}

}}

{{#ifneq | quran | None |

{{#ifneq | | | | }}

}}

{{#ifneq | udhr | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus4}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus5}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus6}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus7}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus8}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus9}}} | None |

{{#ifneq | | | | }}

}}

{{#ifneq | {{{corpus10}}} | None |

{{#ifneq | | | | }}

}}

corpuswordscoverage
<nowinter>azadliq2012</nowinter>azadliq20122.2M ~-%
<nowinter>[[|quran]]</nowinter>quran153K ~-%
<nowinter>[[|udhr]]</nowinter>udhr1.5K ~-%
<nowinter>[[|{{{corpus4}}}]]</nowinter>{{{corpus4}}} ~%
<nowinter>[[|{{{corpus5}}}]]</nowinter>{{{corpus5}}} ~%
<nowinter>[[|{{{corpus6}}}]]</nowinter>{{{corpus6}}} ~%
<nowinter>[[|{{{corpus7}}}]]</nowinter>{{{corpus7}}} ~%
<nowinter>[[|{{{corpus8}}}]]</nowinter>{{{corpus8}}} ~%
<nowinter>[[|{{{corpus9}}}]]</nowinter>{{{corpus9}}} ~%
<nowinter>[[|{{{corpus10}}}]]</nowinter>{{{corpus10}}} ~%

What works? What does not?[edit]

Verbal moods and tenses
Works Minor Problems Absent
Present Progressive (alıram) negative doesn't work well
Imperative Works!
Future indicative (alacağım) 1p and 1s devoicing
Evidential/Past perfect (almışam) Works!
Indefinite future / Aorist (alaram) <t_aor> Works!
Optative present(alam) Works!
Optative past (ala idim) Works!
Necessitative present (almalıyım) Works
Necessitative past (almalı idim) Works
Abilitative(bil-) has to be split
i- copula (idim) Works


Noun Inflection
Works Minor Problems Absent
Cases (n, g, d, acc, abl, loc) Works!
Number (-lAr) Works!
-l Devoicing
-L<A> Works!
-L Works!
-C<A> (makes things like italyanca, inglizce) Works!
Possessives Works!
-ki realized as k Works!

Known problems[edit]

Phonology[edit]

  1. should be replaced by and <k>, and not simply by "q" and "k"
  2. Devoicing should be expanded, adding