Natural language processing (NLP) is a key technique in Business Process Management (BPM). The performance of BPM methods, which are based on NLP, is limited by the accuracy of automatic part-of-speech tagging, a base subtask of NLP.[9] The automatic partof-speech tagging is the process of assigning a tag to every word in a text or a document.[1] I have developed and presented in this paper an application that learns to correctly predict parts-of-speech for words within a sentence using a machine learning algorithm. For this I used a pre-labeled data set (Brown Corpus) and implemented, evaluated and compared several versions of the n-Gram algorithm with the aim of obtaining the best classification accuracy of the automatic part-of-speech tagging process.
