This resource is a dictionary of Modern Turkish, comprised of the definitions of over 50.000 individual entries. Each entry is matched with its corresponding synset (set of synonymous words and expressions) in the Turkish WordNet, KeNet.
The bare-forms in the lexicon consists of nouns, adjectives, verbs, adverbs, shortcuts, etc. Each bare-form appears the same in the lexicon except verbs. Since the bare-forms of the verbs in Turkish do not have the infinitive affix ‘mAk’, our lexicon includes all verbs without the infinitive affix. The bare-forms with diacritics are included in two forms, with and without diacritics. For example, noun ‘rüzgar’ appear both as ‘rüzgar’ and ‘rüzgâr’.
Special markers are included as bare-forms such as doc, s, etc.
Some compound words are included in their affixed form. For instance, ‘acemlalesi’ appears as it is, but not as ‘acemlale’.
Foreign words, especially proper noun foreign words, are included, so that the system can easily recognize them as proper nouns. For instance, the words ‘abbott’, ‘abbigail’ are example foreign proper nouns. Including foreign proper nouns, there are 19,000 proper nouns in our lexicon.
From derivational suffixes, we only include words which has taken -lI, -sIz, -CI, -lIk, and -CIlIk derivational affixes. For example, the bare-forms ‘abacı’, ‘abdallık’, ‘abdestli’ and ‘abdestlilik’, are included, since they have taken one or more derivational affixes listed above.
Each bare-form has a set of attributes. For instance, ‘abacı’ is a noun, therefore, it includes CL_ISIM attribute. Similarly, ‘abdestli’ is an adjective, which includes IS_ADJ attribute. If the bare-form has homonyms with different part of speech tags, all corresponding attributes are included.
| Name | Purpose |
|---|---|
| CL ISIM, CL FIIL, IS_OA | Part of speech tag(s) |
| IS_DUP | Part of a duplicate form |
| IS_KIS | Abbreviation, which does not obey vowel harmony while taking suffixes. |
| IS_UU, IS_UUU | Does not obey vowel harmony while taking suffixes. |
| IS_BILES | A portmanteau word in affixed form, such as ‘adamotu’ |
| IS_B_SI | A portmanteau word ending with ‘sı’, such as ‘acemlalesi’ |
| IS_CA | Already in a plural form, therefore can not take plural suffixes such as ‘ler’ or ‘lar’. |
| IS_ST | The second consonant undergoes a resyllabification. |
| IS_UD, IS_UDD, F_UD | Includes vowel epenthesis. |
| IS_KG | Ends with a ‘k’, and when it is followed by a vowel-initial suffix, the final ‘k’ is replaced with a ‘g’. |
| IS_SD, IS_SDD, F_SD | Final consonant gets devoiced during vowel-initial suffixation. |
| F GUD, F_GUDO | The verb bare-form includes vowel reduction. |
| F1P1, F1P1-NO-REF | A verb, and depending on this attribute, the verb can (or can not) take causative suffix, factitive suffix, passive suffix etc. |
You can also see Python, Cython, C++, Swift, C, Js, or C# repository.
- Java Development Kit 8 or higher, Open JDK or Oracle JDK
- Maven
- Git
To check if you have a compatible version of Java installed, use the following command:
java -version
If you don't have a compatible version, you can download either Oracle JDK or OpenJDK
To check if you have Maven installed, use the following command:
mvn --version
To install Maven, you can follow the instructions here.
Install the latest version of Git.
In order to work on code, create a fork from GitHub page. Use Git for cloning the code to your local or below line for Ubuntu:
git clone <your-fork-git-link>
A directory called Dictionary will be created. Or you can use below link for exploring the code:
git clone https://github.com/olcaytaner/Dictionary.git
Steps for opening the cloned project:
- Start IDE
- Select File | Open from main menu
- Choose
Dictionary/pom.xmlfile - Select open as project option
- Couple of seconds, dependencies with Maven will be downloaded.
From IDE
After being done with the downloading and Maven indexing, select Build Project option from Build menu. After compilation process, user can run Dictionary.
From Console
Go to Dictionary directory and compile with
mvn compile
From IDE
Use package of 'Lifecycle' from maven window on the right and from Dictionary root module.
From Console
Use below line to generate jar file:
mvn install
<dependency>
<groupId>io.github.starlangsoftware</groupId>
<artifactId>Dictionary</artifactId>
<version>1.0.36</version>
</dependency>
Dictionary is used in order to load Turkish dictionary or a domain specific dictionary. In addition, misspelled words and the true forms of the misspelled words can also be loaded.
To load the Turkish dictionary and the misspelled words dictionary,
a = TxtDictionary()
To load the domain specific dictionary and the misspelled words dictionary,
TxtDictionary(String fileName, WordComparator comparator, String misspelledFileName)
And to see if the dictionary involves a specific word, Word getWord is used.
Word getWord(String name)
The word features: To see whether the TxtWord class of the dictionary is a noun or not,
boolean isNominal()
To see whether it is an adjective,
boolean isAdjective()
To see whether it is a portmanteau word,
boolean isPortmanteau()
To see whether it obeys vowel harmony,
notObeysVowelHarmonyDuringAgglutination
And, to see whether it softens when it get affixes, the following is used.
boolean rootSoftenDuringSuffixation()
To syllabify the word, SyllableList class is used.
SyllableList(String word)
@inproceedings{yildiz-etal-2019-open,
title = "An Open, Extendible, and Fast {T}urkish Morphological Analyzer",
author = {Y{\i}ld{\i}z, Olcay Taner and
Avar, Beg{\"u}m and
Ercan, G{\"o}khan},
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://www.aclweb.org/anthology/R19-1156",
doi = "10.26615/978-954-452-056-4_156",
pages = "1364--1372",
}