From 4921f3e8938b5c219b0481870e1b33b291659bd5 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Thu, 24 Apr 2014 18:47:24 +0200
Subject: parse-stanford

---
 parse-stanford.sh | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100755 parse-stanford.sh

diff --git a/parse-stanford.sh b/parse-stanford.sh
new file mode 100755
index 0000000..f8d4210
--- /dev/null
+++ b/parse-stanford.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+
+if [ $# != 1 ]; then
+	echo "$0 text-file" 
+	exit 1
+fi
+
+export CLASSPATH=:/toolbox/stanfordparser_3_2_0/*
+
+IN=$1
+
+cat $IN | java -server -mx25000m  edu.stanford.nlp.parser.lexparser.LexicalizedParser -nthreads 8 -sentences newline -encoding utf-8 -tokenized -outputFormat "typedDependencies" -outputFormatOptions "basicDependencies" edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz - | tr '\n' '\t' | sed 's/\t\t/\n/g' | sed 's/\t/ /g' | sed 's/ *$//' | sed 's/, /,/g' > $IN.stp
+
-- 
cgit v1.2.3