Looking for a new company or product name? Writing a fiction novel and inventing new slang? Combine two words into one with the Word Blender.
Like the Name Blender, the Word Blender combines two words into one. The Word Blender works by enumerating all combinations of the supplied start words. Each new combination is then scored against a language score with additional edit distance component. Language models are stastical modals that can determine how likely a string of characters is to occur naturally in a given language. The language model helps the word blender identify which of the newly generated combinations are more natural, and thus likely easier to pronouce. The edit distance component rewards combinations that more closely match each of the supplied start words. Combiantions below a certain threshold are discarded.
The language score is created by useing language model with Kneser-Ney smoothing to model the probability character sequences (n-grams) of a string. n-gram frequencies are determined by analyzing the word frequencies from the Project Gutenberg frequent word list.