Language in 10 minutes:

Turkish
Adi Renduchintala
Outline
● Demographics
● History
● Phonology (very briefly)
● Grammar
○ Nouns, Verbs, Adjectives
○ Negation
○ Word Order
○ Unique aspects of Morphology & Syntax
● Machine Translation
○ Challenges
○ Corpora
○ State of the art
Demographics
● 63 million speakers
● Apart from Turkey, spoken in
Bulgaria, Cyprus, Greece,
Macedonia, Romania, and
Serbia.
● 2 million speakers in Germany,
and large Turkish speaking
population in USA
History
● Oldest record of written Old Turkic (8th
century)
○ Göktürk (Köktürk) tribe of central Asia
○ Chinese and Old Turkic Inscriptions
○ Parallel Text of verses, telling the story
of the tribes rebellion against Chinese
emperor (Tang Dynasty)
● Spread over central asia, eastern europe
and the middle east
● “Ottoman Turkish” became the official
language of the Ottoman Empire (11th
century)
History
● “Ottoman Turkish” mix of Kaba, Persian,
and Arabic
● Kaba associated with lower social status
of the period
● 19th century saw the collapse of the
Ottoman empire and the creation of the
Republic of Turkey
● Kaba became the bases of modern
Turkish.
● Script was also romanized.
Phonology: Vowel Harmony
● Vowel Harmony (Constraints on closely located vowels)
● Vowels : 〈a〉, 〈e〉, 〈ı〉, 〈i〉, 〈o〉, 〈ö〉, 〈u〉, 〈ü〉
○ twofold (-e/-a) the locative suffix, for example, is -de after front vowels
and -da after back vowels.
○ fourfold (-i/-ı/-ü/-u): the genitive suffix
● -XeY can take the form -XeY or XaY
● -XiY can take the form -XiY ,-XıY , -XüY , or -XuY
 Grammar: Nouns
Case Endings Example Meaning

Village Tree

Nominative köy ağaç (the) village/tree

Genitive -in (-ın -ün -un) köyün ağacın the village’s/tree’s

of the village/tree

Dative -e (-a) köye ağaca to the village/tree

Accusative -i (-ı -ü -u) köyü ağacı the village/tree

Ablative -den (-dan) köyden ağaçtan from the village/tree

Locative -de (-da) köyde ağaçta in the village/on the

tree

source: http://en.wikipedia.org/wiki/Turkish_language
 Grammar: Nouns
Turkish +Morpheme Surface English

ev (the) house

ev +ler (+lar) evler (the) houses

ev +in evin your (sing.) house

ev +iniz eviniz your (pl./formal)

house

ev +im evim my house

ev +im +de evimde at my house

ev +im +de +im evimdeyim I am at my house.

source: http://en.wikipedia.org/wiki/Turkish_language
Grammar: Adjectives
● Adjectives are not declined*
● Unless they are used as nouns (in which case they are declined)
● Can be placed before or after a noun
○ mavi ev - the blue house
○ ev, mavi - the house is blue (statement of fact)

*Declension: the inflection of nouns, pronouns, adjectives, and articles to indicate number, case, and
gender.
 Grammar: Verbs
● Can be inflected to indicate:
○ tense
○ mood
○ aspect
○ negation
■ -değil (to be)
● Türküm = i am Turkish,
● Türk değilim = i am not Turkish.
■ -me (all others)
Grammar: Word Order
● Turkish is mostly SOV
● Some constraints
○ Definite article (the) precedes the indefinite (a)
○ for eg:
■ hikâyeyi bir çocuğa anlattı
■ "she told the story to a child”
■ “she told a story to the child”
Unique Aspects: Mirativity
Mirativity: shows how familiar a speaker is with a piece of information.

Turkish Kemal gel-di Turkish Kemal gel-mIs

Morphosyntax Kemal came Morphosyntax Kemal came, MIRATIVE
Translation Kemal came. Translation Kemal, surprisingly, came

Payne, Thomas Edward. Describing morphosyntax: A guide for field linguists. Cambridge University Press, 1997. 178-9.
Unique Aspects: Causativity
Morphological causatives: increase valence (change the argument structure of
a verb so that it takes additional arguments)

Turkish Hasan öl dü Turkish Ali Hassan-t öl-dür-dü

Morphosyntax die-NON Morphosyntax die - CAUSATIVE

CAUSATIVE

Translation Hasan died. Translation Ali killed Hassan

Payne, Thomas Edward. Describing morphosyntax: A guide for field linguists. Cambridge University Press, 1997. 178-9.
Unique Aspects: Existentials
Existentials refer to the existence of something.
● special verb for existentials
● special verb for negating existentials

Positive Existential Negative Existential

Turkish kösede bir kahve var Turkish kösede bir kahve yok

Morphosyntax on:corner a book EXIST Morphosyntax on:corner a book LACK

Translation There is a book on the corner. Translation There isn’t a book on the corner.

Payne, Thomas Edward. Describing morphosyntax: A guide for field linguists. Cambridge University Press, 1997. 124.
 MT: Challenges
● Language Modeling: naive LM models will produce high
OOV rate.
● Alignment is challenging when source and target have
large difference in lengths.
● “BLEU will kill you if you get a single morpheme wrong”
-K Oflazer

http://www.andrew.cmu.edu/user/ko/downloads/lrec.pdf
Corpora
● The Swedish-Turkish Parallel Corpus and Tools for its Creation (LREC?)
● Turkish English parallel text from Kemal Oflazer (COLING 08)
● Turkish Wordnet
● TS Corpus
● LDC: ECI Multilingual Text
● OPUS: KDEdoc ( ~226 bitexts)
● OPUS: KDE ( ~1800 bitexts)
● OPUS: PHP ( ~230 bitexts)
State of the art
● Eyigoz et al (ACL 2013)
○ 50K sentences from Turkish Ministry of Foreign Affairs Documents
○ English to Turkish : 22.52
○ Turkish to English : 29.98
● Any other published results of open corpora?
 Thank you!
Teşekkür ederiz!