Input a piece of text, get back the same piece of text with the parts of speech tagged according to the Stanford CoreNLP MaxEnt Tagger. You can find a large list of pretrained taggers in the "data://StanfordNLP/models/" directory, including English (multiple taggers), Arabic, German, Chinese, and Spanish. If you do not specify a tagger model a default English one will be used.
Parts are tagged according to the conventions of the Penn Treebank Project (http://www.cis.upenn.edu/~treebank/
). For example, a plural noun is denoted NNS, a singular or mass noun is NN, and a determiner (such as a/an
, etc.) as DT.
For more information, please refer tohttp://nlp.stanford.edu/software/corenlp.shtml or Manning, Christopher D., Surdeanu, Mihai, Bauer, John, Finkel, Jenny, Bethard, Steven J., and McClosky, David. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55-60.