;; from http://www.codeproject.com/csharp/englishparsing.asp
;; http://www.comp.leeds.ac.uk/amalgam/tagsets/upenn.html
;; http://bulba.sdsu.edu/jeanette/thesis/PennTags.html (look like the best)
;; http://citeseer.ist.psu.edu/cache/papers/cs/17420/ftp:zSzzSzftp.cis.upenn.eduzSzpubzSztreebankzSzdoczSzmanualzSzroot.pdf/bies95bracketing.pdf
;; ftp://ftp.cis.upenn.edu/pub/treebank/doc/tagguide.ps.gz 

(defparameter *penn-tags*
  '("CC" "Coordinating conjunction"
    "RP" "Particle"
    "CD" "Cardinal number"
    "SYM" "Symbol"
    "DT" "Determiner"
    "TO" "to"
    "EX" "Existential there"
    "UH" "Interjection"
    "FW" "Foreign word"
    "VB" "Verb, base form"
    "IN" "Preposition/subordinate conjunction"
    "VBD" "Verb, past tense"
    "JJ" "Adjective"
    "VBG" "Verb, gerund/present participle"
    "JJR" "Adjective, comparative"
    "VBN" "Verb, past participle"
    "JJS" "Adjective, superlative"
    "VBP" "Verb, non-3rd ps. sing. present"
    "LS" "List item marker"
    "VBZ" "Verb, 3rd ps. sing. present"
    "MD" "Modal"
    "WDT" "wh-determiner"
    "NN" "Noun, singular or mass"
    "WP" "wh-pronoun"
    "NNP" "Proper noun, singular"
    "WP$" "Possessive wh-pronoun"
    "NNPS" "Proper noun, plural"
    "WRB" "wh-adverb"
    "NNS" "Noun, plural"
    "``" "Left open double quote"
    "PDT" "Predeterminer     "
    "," "Comma"
    "POS" "Possessive ending "
    "''" "Right close double quote"
    "PRP" "Personal pronoun"
    "." "Sentence-final punctuation"
    "PRP$" "Possessive pronoun"
    ":" "Colon, semi-colon"
    "RB" "Adverb"
    "$" "Dollar sign"
    "RBR" "Adverb, comparative"
    "#" "Pound sign"
    "RBS" "Adverb, superlative"
    "-LRB-" "Left parenthesis"
    "-RRB-" "Right parenthesis"
    "S" "Sentence"
    "VP" "Verb phrase"
    "NP" "Noun phrase"
    "PP" "Preposition phrase"
    "ADVP" "Adverb phrase"
    "ADJP" "Adjective phrase"
    "TOP" "TOP"
    "SBAR" "Clause introduced by a (possibly empty) subordinating conjunction"
    "INC" "hmm... what does this mean - no parse?"
    "PRN" "Parenthetical"
    ))

(loop for (token full) on  *penn-tags* by 'cddr
     do (setf (get (intern token 'keyword) 'tag-desc) full))

(defun tagdoc (tag)
  (get tag 'tag-desc))