CQP –  Corpus Query Processor  TNC -

12 
Abstract
This diploma paper presents the results and discussions of one of the three special forms of 
verbs in the Kyrgyz language, id est ‘Atoochtuk’ or verbal adjectives. More precisely, the study 
deals with POS annotation of ‘Atoochtuk’ (Verbal Adjectives), which has an uncertain status in 
the newly created Kyrgyz corpus. The annotation of this part of speech is performed using an 
open source machine translation platform “Turkic Apertium”.
The aim of this work is to clarify and determine the annotation of verbal adjective 
‘Atoochtuk’, which combines the grammatical features of both adjective and verb. In order to 
enhance the effectiveness of the corpus as a research tool, it is necessary to define and clarify all 
morphological properties of the Kyrgyz language. However, the experience on creating a new 
Kyrgyz corpus has caused new challenges, including tagging of the Kyrgyz ‘Atoochtuk’ in 
respect what symbols should be selected in order to obtain its reliable and correct adaptation to a 
certain toolkit (UPENN, Apertium, Universal Features, Leipzig tagsets, etc.).
Thus, an attempt has been made to annotate and adapt Kyrgyz special forms of verbs which 
function as substitutional or additional elements of verbs and nouns (Verbal Adjective, Verbal 
Adverb, Verbal Noun), leaning on the tools from Turkic Lexicon Apertium. So, after a long 
disputes and discussions, the decision has been taken to label ‘Atoochtuk’ as ‘gpr’, i.e., 
‘глагольное прилагательное’. 
Unfortunately, up until now not so much work has been accomplished in creating and 
developing Kyrgyz corpus as well as an issue dealing with the field of corpus linguistics in 
Kyrgyzstan. I believe that this study will significantly contribute to solving multiple problems 
that are encountered while annotating and tagging special features such as ‘Atoochtuk’. Along 
with all these, the thesis will be extremely topical in developing and improving the Kyrgyz 
Corpus. This study will also contribute to the origin and development of Corpus Linguistics as a 
new branch of Linguistics in Kyrgyzstan.

жүктеу/скачать 1,4 Mb.

Достарыңызбен бөлісу: