Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


For Developers



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.

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 SpellChecker will be created. Or you can use below link for exploring the code:

git clone

Open project with IntelliJ IDEA

Steps for opening the cloned project:

  • Start IDE
  • Select File | Open from main menu
  • Choose NGram/pom.xml file
  • 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 NGram.

From Console

Use below line to generate jar file:

 mvn install


Maven Usage


Training NGram

  • NGram can be created and trained either by using addNGram() method or using a Corpus as follows:

    • Using addNGram(),

        Sentence sentence = new Sentence("Yarın okula gideceğim");
        NGram ngram = new NGram(1);
    • Using a Corpus,

        Corpus corpus = new Corpus("corpus.txt"); 
        NGram ngram = new NGram(corpus.getAllWordsAsArrayList(), 1);
  • To use Corpus, snippet below should be added to dependencies.

  • To calculate probabilities, there are possible smoothing methods. These smoothing methods are divided into two categories as SimpleSmoothing and TrainedSmoothing. Their usages are as follows:

    • SimpleSmooting methods are:

      • LaplaceSmoothing

          ngram.calculateNGramProbabilities(new LaplaceSmoothing());
      • GoodTuringSmoothing

          ngram.calculateNGramProbabilities(new GoodTuringSmoothing());
      • NoSmoothing

          ngram.calculateNGramProbabilities(new NoSmoothing());
      • NoSmoothingWithDictionary

        A dictionary of nonrare words are required to initialize this. This can be created as follows and then probabilities can be calculated:

          HashSet<Symbol> dictionary = ngram.constructDictionaryWithNonRareWords(1, 0.1);
          ngram.calculateNGramProbabilities(new NoSmoothingWithDictionary(dictionary));
      • NoSmoothingWithNonRareWords

          ngram.calculateNGramProbabilities(new NoSmoothingWithNonRareWords(0.1));
    • TrainedSmoothing methods are:

      • AdditiveSmoothing

          ngram.calculateNGramProbabilities(corpus.getAllWordsAsArrayList(), new InterpolatedSmoothing());
      • InterpolatedSmoothing

          ngram.calculateNGramProbabilities(corpus.getAllWordsAsArrayList(), new AdditiveSmoothing<>());

Saving NGram

  • NGrams can be saved to a file as follows:"ngram.model");

Loading NGram

  • Loading from an existing model:

      try {
          FileInputStream inFile = new FileInputStream("ngram.model");  
          ObjectInputStream inObject = new ObjectInputStream(inFile);
          NGram ngram = (NGram<Word>) inObject.readObject();
      }catch (IOException | ClassNotFoundException e) {
You can’t perform that action at this time.