| Module Info
| Add a review of Lingua-EN-Tagger
From a non-academic, non-linguistic point of view, this module can return you some useful keywords/less common words from a block of text, and has proved useful in automated indexing and tagging.
However, be warned that it requires its input to be in memory, rather than from a file, which has implications for large bodies of text, since simply chunking the text and re-invoking will prevent the module functioning correctly.
It is a good implementation of the PennTreebank + HMM, to identify the POS of words. It also determines noun phrases too!