I'm using the Stanford POS tagger to process German text and I'm interested in assessing the number (singular/plural) of the nouns in the sentence, so that I can classify them accordingly. This is achievable for English sentences as the tags used for singular nouns and plural nouns differ. But when using the model for German tags, I get the same tags for singular and plural. This probably has to do with the fact that the English model is trained with Penn Treebank tags, which has the NN and NNS tags for example. How can I get this sort of information for German text by using the Stanford CoreNLP tools?