Software/Tagger

Description

The Tagger annotates tokens by assigning word class labels to them. This enables you to distinguish between nouns and verbs, and also is an important step in recognising the structure of a sentence.

The Tagger uses probabilities to assign the most likely tag. This is done by first looking at the word in isolation, and then taking into account the surrounding context.

This algorithm is in principle language independent. However, at present there are only resource files available to use it on English data.

For the API see the javadoc generated documentation.

To buy this (or other components) proceed to the distribution page.