From 645b794d5941177b206ba97355c1861e367e2e69 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@cab.ark.cs.cmu.edu>
Date: Tue, 2 Oct 2012 01:16:32 -0400
Subject: note to self

---
 python/README.md | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'python')

diff --git a/python/README.md b/python/README.md
index da9f9387..bea6190a 100644
--- a/python/README.md
+++ b/python/README.md
@@ -12,6 +12,10 @@ Compile a parallel corpus and a word alignment into a suffix array representatio
 
 	python -m cdec.sa.compile -f f.txt -e e.txt -a a.txt -o output/ -c extract.ini
 
+Or, if your parallel corpus is in a single-file format (with source and target sentences on a single line, separated by a triple pipe `|||`), use:
+
+	python -m cdec.sa.compile -b f-e.txt -a a.txt -o output/ -c extract.ini
+
 Extract grammar rules from the compiled corpus:
 	
 	cat input.txt | python -m cdec.sa.extract -c extract.ini -g grammars/
-- 
cgit v1.2.3