Turkish Spell Checker

This tool is a spelling checker for Modern Turkish. It detects spelling errors and corrects them appropriately, through its list of misspellings and matching to the Turkish dictionary.

Video Lectures

For Developers

You can also see Java, Python, Cython, Swift, Js, or C++ repository.

Requirements

• C# Editor
• Git

Git

Install the latest version of Git.

Download Code

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 TurkishSpellChecker-CS will be created. Or you can use below link for exploring the code:

git clone https://github.com/starlangsoftware/TurkishSpellChecker-CS.git

Open project with Rider IDE

To import projects from Git with version control:

• Open Rider IDE, select Get From Version Control.

• In the Import window, click URL tab and paste github URL.

• Click open as Project.

Result: The imported project is listed in the Project Explorer view and files are loaded.

Compile

From IDE

After being done with the downloading and opening project, select Build Solution option from Build menu. After compilation process, user can run TurkishSpellChecker-CS.

Detailed Description

• Creating SpellChecker
• Spell Correction

Creating SpellChecker

SpellChecker finds spelling errors and corrects them in Turkish. There are two types of spell checker available:

• SimpleSpellChecker

  • To instantiate this, a FsmMorphologicalAnalyzer is needed.

      FsmMorphologicalAnalyzer fsm = new FsmMorphologicalAnalyzer();
      SpellChecker spellChecker = new SimpleSpellChecker(fsm);   
    

• NGramSpellChecker,

  • To create an instance of this, both a FsmMorphologicalAnalyzer and a NGram is required.

  • FsmMorphologicalAnalyzer can be instantiated as follows:

      FsmMorphologicalAnalyzer fsm = new FsmMorphologicalAnalyzer();
    

  • NGram can be either trained from scratch or loaded from an existing model.

    • Training from scratch:

        Corpus corpus = new Corpus("corpus.txt"); 
        NGram ngram = new NGram(corpus.GetAllWordsAsArrayList(), 1);
        ngram.CalculateNGramProbabilities(LaplaceSmoothing());
      

    There are many smoothing methods available. For other smoothing methods, check here.

    • Loading from an existing model:

        NGram ngram = new NGram("ngram.txt");
      

  For further details, please check here.

  • Afterwards, NGramSpellChecker can be created as below:

      SpellChecker spellChecker = new NGramSpellChecker(fsm, ngram);
    

Spell Correction

Spell correction can be done as follows:

Sentence sentence = new Sentence("Dıktor olaç yazdı");
Sentence corrected = spellChecker.SpellCheck(sentence);
Console.WriteLine(corrected);

Output:

Doktor ilaç yazdı