Created
November 6, 2012 19:13
-
-
Save damionjunk/4026818 to your computer and use it in GitHub Desktop.
Generate a gold standard file and text extraction for evalb / Assignment 8
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(ns ptreader | |
(:require [clojure.java.io :as io] | |
[clojure.string :as s]) | |
(:import [edu.stanford.nlp.ling Word WordTag] | |
[edu.stanford.nlp.trees PennTreeReader])) | |
(defn get-sentence | |
[words] | |
(s/join " "(map (fn [w] (.word w)) words))) | |
(comment | |
(let [fp "/Users/djunk/projects/L645/hw08/wsj_all.mrg" | |
ptr (PennTreeReader. (io/reader fp)) | |
tree (.readTree ptr)] | |
(with-open [gold (io/writer "/Users/djunk/projects/L645/hw08/wsj00-gold.mrg") | |
text (io/writer "/Users/djunk/projects/L645/hw08/wsj00-text.txt")] | |
(loop [tree (.readTree ptr)] | |
(if (not (nil? tree)) | |
(let [psgold (.toString tree) | |
words (.yieldWords tree)] | |
(.write text (str (get-sentence words) "\n")) | |
(.write gold (str psgold "\n" )) | |
(recur (.readTree ptr))) | |
)))) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment