DocumentAnalytics.NaturalLanguageClassifier actions

Natural Language Classifier is an IBM Watson service, which can be trained to classify documents or sections of documents. That based on the text that is contained in the document or the section of a document. The default instance name: DocumentAnalytics.NaturalLanguageClassifierActions.

To do this, you must first create and train a classifier using some representative set of training data containing text from a set of sample documents. Once the classifier has been trained, you can give it other similar documents and classifier attempts to classify them according to its training. The Classifier returns a confidence score that is associated with the classification.

Because Natural Language Classifier works on the text of the document, you must first perform OCR on the document before calling the Classify action to do the classification.

Properties and methods: