I emailed Fei Xia and she said that MSP simply means miscallenous particles. I don't think it actually means anything more special, like "modal structural particle," or otherwise.
Page 17 of the attached file is what you put on the question already.
Simply put, they're just not as good. Lookup taggers can't deal with the fact that words can have multiple parts of speech: look at "project" in English, which can be a verb or a noun. A lookup tagger can't distinguish between those two and will always choose whichever was most common in its training corpus.
N-gram taggers try to deal with this problem by ...
Chapter 5 of the online NLTK book explains the concepts and procedures you would use to create a tagged corpus.
There are several taggers which can use a tagged corpus to build a tagger for a new language. You will probably want to experiment with at least a few of them.
A tagged corpus is better than just a list of words because many languages have ...
In English the categories of noun and verb aren't that clearly cut. You can use most nouns as verbs, if the semantic information you intend to transmit is understood. This usage is completely normal and regular: to give a contrived example, you could say English is nouning verbs (forced chuckles abound).
This is usually considered derivation by way of a ...
Whichever corpus is reasonably large and correctly annotated and has similar content to what the tagger will actually be used on. (Maybe you can be more specific about what you need.)
Realistically you may want to train on or find a pretrained model trained on a more general corpus that is larger, and the fine-tune on a presumably smaller more targetted ...
From a part of speech perspective, you'll be interested in the the tags that begin with "W" found here: https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
However, the PoS tags won't be enough. Consder a sentence like,
Bob is the person who ate the cake.
The sentence isn't interrogative but the "who" will trigger the PoS logic. ...
You are right. There only 'whose' is possessive:
The tag for WHOSE is WPRO$.
he_PRO asked_VBD hir_PRO ... whos_WPRO$ was_BED the_D child_N within_P
and_CONJ by_P whoos_WPRO$ commandement_N
Look up here for more explanations of the Pen tagset:
In a word, if you don't know, you have to guess, then try to verify your guess. You will probably use some heuristics (that is, rules of thumb) to guide your guesswork. At least, as a linguist, that's what I do, and I think it is a plausible model for what any hearer does in figuring out what is being said. Your first guesses will lead to further guesses ...
The function word "of" is sometimes difficult to classify, think of cases like
to be aware of something, to be fond of something/someone, or because of. Putting it in a category of its own reduces the errors of misclassification.
CLTK is producing parsing programs for classical Languages. Information on the LATIN version, including the copyright notice, can be found at kyle-p-johnson (notebooks):
Information is posted in a nine-letter string.
Each position in the sequence signifies a category.
Nine string sequence:
.1. part of speech .2.person .3.number .4.tense .5.mood .6....
It refers to the set of "correct" part of speech tags assigned to the tokens (words and punctuation) in a corpus of sentences. The tags are usually annotated and vetted manually by linguistic experts, and used to train and test classifiers, parsers and other processing resources used to process natural language.