The paragraph and sentence splitter are two components which split an input text accordingly, applying tags to the resulting segments. Both of the components can be used online, as well as in other applications through the use of web-services.
More information about the paragraph splitter can be found here.
Information about the sentence splitter is available here here.
The tokeniser is a tool, which given an input string, it breaks it down into meaningful tokens. These being words, numbers and other symbols. The resulting list can be then used for further processing.
This tool is designed to operate on Maltese text!
For further information, please go here.
Using a statistical part of speech (POS) tagger implementation, TnT, and training it on manually tagged text, the Maltese tagger has an accuracy of 96%. A specific tag set is used by this tool.
More information on the POS tagger can be found here.
Information on the Chunker can be found here.