4
votes
Accepted
Why not use a Lookup taggers?
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 ...
4
votes
Accepted
What does 'MSP' stand for in the context of Chinese parts of speech?
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 ...
4
votes
Why is 's a verb?
Because "that's" can always be replaced by "that is". When 's is not a possessive, it is a shortened version of "is" or "has" (or, in rapid speech after what and when, "does").
3
votes
Accepted
What exactly is meant by "part of speech" (POS) in linguistics and NLP?
One purpose of parts-of-speech is to simplify grammatical descriptions. They group together words that behave in a similar way, and their behaviours can then be more easily described in rules. They ...
3
votes
Accepted
Why is 's a verb?
Are these two sentences the same to you?
It's fine.
It is fine.
If so, then I would claim that they are synonymous because 's is written shorthand for is. Is is the verb to be in English.
3
votes
How to tag_pos in nltk for a language that is not English?
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 ...
2
votes
Which is the most recommended corpus for training a POS Tagger?
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 ...
2
votes
How to derive that a sentence is a question from parts of speech
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 ...
1
vote
What exactly is meant by "part of speech" (POS) in linguistics and NLP?
"Part of speech" is only marginally recognized in theoretical linguistics, instead linguists deal in features, and then perhaps offer informal recognitions of traditional parts of speech in ...
1
vote
Possessive vs non possesive WH-pronouns
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
her_PRO$ body_N
and_CONJ by_P whoos_WPRO$ ...
1
vote
Why are prepositions and subordinate conjunctions grouped as the same tag in the Penn Treebank tag set?
Look up here:
Complements of P
PPs are headed by prepositions and take complements of various categories. The most common are NP and CP, but ADJP, ADVP, IP, PP, etc. are possible as well. Since ...
1
vote
How can you know that a word in a sentence is a verb?
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'...
1
vote
How can you know that a word in a sentence is a verb?
Yes, with probabilistic parsing and part-of-speech tagging.
See:
https://en.wikipedia.org/wiki/Parsing#Human_languages
https://en.wikipedia.org/wiki/Part-of-speech_tagging
https://en.wikipedia.org/...
1
vote
Accepted
Why does the CLAWS5 tagset separate "of" from all other prepositions?
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 ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
pos-tagging × 19computational-linguistics × 10
parts-of-speech × 10
corpora × 2
resource-request × 2
pronouns × 2
wh-words × 2
syntax × 1
terminology × 1
grammar × 1
verbs × 1
latin × 1
german × 1
chinese × 1
nouns × 1
parsing × 1
words × 1
prepositions × 1
sentences × 1
determiners × 1
conjunctions × 1
computer-science × 1
particles × 1
nltk × 1
language-models × 1