en-tweet.README

en-tweet is a mapping into Petrov et al.'s universal tagset from the tagset 
used in the corpus of English Twitter messages published as

  Kevin Gimpel, Nathan Schneider, Brendan O’Connor, Dipanjan Das, Daniel Mills, 
  Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, and 
  Noah A. Smith (2011). Part-of-Speech Tagging for Twitter: Annotation, 
  Features, and Experiments. Proc. of ACL.

We summarize the tagset here for convenience:

Nominal, Nominal + Verbal
N	common noun
O	pronoun (personal/WH; not possessive)
S	nominal + possessive
ˆ	proper noun
Z	proper noun + possessive
L	nominal + verbal
M	proper noun + verbal

Other open-class words
V	verb incl. copula, auxiliaries
A	adjective
R	adverb
!	interjection

Other closed-class words
D	determiner
P	pre- or postposition, or subordinating conjunction
&	coordinating conjunction
T	verb particle
X	existential there, predeterminers
Y	X + verbal

Twitter/online-specific
#	hashtag (indicates topic/category for tweet)
@	at-mention (indicates another user as a recipient of a tweet)
~	discourse marker, indications of continuation of a message across multiple tweets
U	URL or email address
E	emoticon

Miscellaneous
$	numeral (CD)
,	punctuation
G	other abbreviations, foreign words, possessive endings, symbols, garbage


See http://www.ark.cs.cmu.edu/TweetNLP/ for more information.

- Nathan Schneider, 2011-05-06