Clojure + Stanford ParserでS式を読み込んで色々操作する例

penn.clj

(import edu.stanford.nlp.trees.PennTreeReader)

(let [filename "/Users/yasuhisa/Desktop/PENN_TREEBANK3/PARSED/MRG/WSJ/00/WSJ_0001.MRG"]
  (with-open [rdr (clojure.java.io/reader filename)]
    (let [ptr (new PennTreeReader rdr)
          trees (loop [result []]
                  (if-let [t (.readTree ptr)]
                    (recur (conj result t))
                    result))]
      (for [^LabeledScoredTreeNode t trees]
        (for [leaf (.getLeaves t)]
          (.nodeString leaf))))))

;; (("Pierre" "Vinken" "," "61" "years" "old" "," "will" "join" "the" "board" "as" "a" "nonexecutive" "director" "Nov." "29" ".")
;;  ("Mr." "Vinken" "is" "chairman" "of" "Elsevier" "N.V." "," "the" "Dutch" "publishing" "group" "."))