Apertium-tat

Tatar - татар теле
language transducer
Coverage:	~91%
Stems:	55,702
Vanilla stems:	54,773
Paradigms:
Location:	apertium-tat (languages)
Families:
Areas:
Lang info	Tatar

Apertium-tat is a morphological analyser/generator and CG tagger for Tatar, currently under development. It is intended to be compatible with transducers for other Turkic languages so that they can be translated between. It's used in the following language pairs:

• Kazakh and Tatar
• Tatar and Bashkir
• Tatar and Russian

Installation

apertium-tat is located in languages/apertium-tat.

You will need HFST, lttoolbox, apertium and vislcg installed on your computer to be able to use it.

The easiest way to get those dependencies is to install them from User:Tino Didriksen's repository (see Prerequisites for Debian or Prerequisites for RPM).

Then you can check out apertium-tat from our svn repository and compile it:

svn co http://svn.code.sf.net/p/apertium/svn/languages/apertium-tat/
cd apertium-tat
./autogen.sh
make

Otherwise, see the Installation page for instructions.

For spell checking

If you're compiling the apertium-tat spell checker, you'll additionally need these dependencies:

• hfst-ospell (./configure --enable-zhfst)
  • libarchive-dev
• corevoikko/libvoikko/src/tools/voikkospell (./configure --enable-hfst)

You'll want to configure apertium-tat with --enable-ospell and then after making it, copy tat.zhfst to ~/.voikko/3/tt.zhfst

Then you can do this:

$ echo "татарча билмим" | sed 's/ /\n/' | voikkospell -d tt -s
C: татарча
W: билмим
S: белмим
S: биелмим
S: бөлмим
S: бирмим
S: бүлмим

Usage

Morphological analysis:

$ echo "барабыз" | apertium -d . tat-morph 
^барабыз/бар<v><iv><pres><p1><pl>$^./.<sent>$

apertium -d . tat-tagger will give disambiguated output, apertium -d . tat-disam – disambiguated output in CG format showing which rules were applied:

$ echo "Без урманга таба барабыз." | apertium -d . tat-disam 
"<Без>"
	"без" prn pers p1 pl nom
;	"без" prn pers p1 pl nom
;		"и" cop p3 pl REMOVE:236
;	"без" prn pers p1 pl nom
;		"и" cop p3 sg REMOVE:236
"<урманга>"
	"урман" n dat
"<таба>"
	"таба" post SELECT:543
;	"таба" n nom
;		"и" cop p3 pl REMOVE:236
;	"таба" n nom
;		"и" cop p3 sg REMOVE:236
;	"таба" n attr REMOVE:452
;	"тап" v tv prc_impf SELECT:543
;	"таба" n nom SELECT:543
;	"тап" v tv pres p3 sg SELECT:543
"<барабыз>"
	"бар" v iv pres p1 pl
"<..>"
	".." sent

If you want to know what exactly each mode does (in our case, modes are "tat-morph", "tat-tagger" and "tat-disam"), have a look at the modes.xml file or the modes/ directory.

Components

• apertium-tat.tat.lexc : lexicon (stems + morphotactics)
• apertium-tat.tat.twol : morphophnological rules
• apertium-tat.tat.rlx : disambiguation rules

Paradigms

= Nouns = 

LEXICON N1               ! Standard noun
LEXICON N1-RUS           ! Noun with Russian phonology (e.g. университет)
LEXICON N-COMPOUND-PX    ! Noun with obligatory possession (e.g. күз% яше)
LEXICON N3               ! Singularia tantum (e.g. Аллаһ)  

= Proper nouns =

LEXICON NP-TOP           ! Toponym (placename)
LEXICON NP-ANT-M         ! Male first name 
LEXICON NP-ANT-F         ! Female first name 
LEXICON NP-COG-M         ! Male фамилия
LEXICON NP-COG-MF        ! Male + female фамилия
LEXICON NP-COG-OB        ! Normal фамилия in -ов / -ев
LEXICON NPCOGFLEX        ! Polish фамилия with -ска
LEXICON NP-PAT-VICH      ! Patronymics in -вич
LEXICON NP-ORG           ! Organisations
LEXICON NP-AL            ! Other proper names.

= Verbs =

LEXICON V-IV-IR          ! Intransitive verbs with aorist in -Iр
LEXICON V-TV-NOPASS-IR   ! Transitive verb without a passive.
LEXICON V-TV-PASS-IR     ! Irregular passive stem of a transitive verb.
LEXICON V-TV-IR          ! Transitive verb with aorist in -Iр
LEXICON V-IV-AR          ! Intransitive verb with aorist in -Ар
LEXICON V-TV-AR          ! Transitive verb with aorist in -Aр


= Adjectives =

LEXICON A1               ! adjectives that can be both substantivized and andverbialized;
                         ! all three readings (<adj>, <adj.subst> and <adj.advl>) have comparison levels.
                         !# яхшы, тиз

LEXICON A2               ! <adj> and <adj.subst> readings have comparison levels.
                         !# иске

LEXICON A3               ! adjectives without adverbial reading & so-called "predicatives" (бар, юк);
                         ! no comparison levels at all.
                         !# язгы, бар, юк

LEXICON A4               ! "pure" adjectives - no adverbial and substantive readings, no comparison levels;

= Adverbs =

LEXICON ADV-LANG         ! languages ('татарча')
LEXICON ADV              ! Normal adverb  
LEXICON ADV-WITH-KI      ! Adverb that can also take -GI
LEXICON ADV-WITH-KI-BIRE ! Adverb that can take -дәге