japerk's profile

A 98.1% accurate simplified tags part-of-speech tagger trained on the brown corpus. It requires Python and NLTK 2.0 and is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License: http://creativecommons.org/licenses/by-nc-sa/3.0/. In addition to punctuation tags, it produces the following tags: ADJADVCNJDET EX FWMOD NNIL NPNUM PPRO ...

A 98.3% accurate Chinese part-of-speech tagger trained on the sinica_treebank corpus. It requires Python & NLTK 2.0 and is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike License: http://creativecommons.org/licenses/by-nc-sa/2.5/

A 99.3% accurate part-of-speech tagger trained on the treebank corpus. It is many times faster than the default NLTK tagger and is a fraction of the size (which means less loading time and lower memory requirements). It requires Python & NLTK 2.0 and is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License: ...