From ed56625e5edeadbe9297680b07e269c42b7ea420 Mon Sep 17 00:00:00 2001
From: Chris Dyer <redpony@gmail.com>
Date: Thu, 27 Feb 2014 19:45:08 -0500
Subject: ptb to normal

---
 corpus/support/quote-norm.pl | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'corpus/support/quote-norm.pl')

diff --git a/corpus/support/quote-norm.pl b/corpus/support/quote-norm.pl
index 1d9bb96f..33604027 100755
--- a/corpus/support/quote-norm.pl
+++ b/corpus/support/quote-norm.pl
@@ -11,6 +11,15 @@ while(<STDIN>) {
   # Delete control characters:
   s/[\x{00}-\x{1f}]//g; 
 
+  # PTB --> normal
+  s/-LRB-/(/g;
+  s/-RRB-/)/g;
+  s/-LSB-/[/g;
+  s/-RSB-/]/g;
+  s/-LCB-/{/g;
+  s/-RCB-/}/g;
+  s/ gon na / gonna /g;
+
   # Regularize named HTML/XML escapes:
   s/&\s*lt\s*;/</gi;    # HTML opening angle bracket
   s/&\s*gt\s*;/>/gi;    # HTML closing angle bracket
-- 
cgit v1.2.3