From 5f89a46858a7f271884d06c6107b65324a92a279 Mon Sep 17 00:00:00 2001
From: graehl <graehl@ec762483-ff6d-05da-a07a-a48fb63a330f>
Date: Wed, 18 Aug 2010 01:58:24 +0000
Subject: home

git-svn-id: https://ws10smt.googlecode.com/svn/trunk@588 ec762483-ff6d-05da-a07a-a48fb63a330f
---
 graehl/NOTES.earley | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'graehl')

diff --git a/graehl/NOTES.earley b/graehl/NOTES.earley
index 9b8bf1fc..6f94f898 100755
--- a/graehl/NOTES.earley
+++ b/graehl/NOTES.earley
@@ -84,3 +84,7 @@ then X[k,i]->rY.s (a',b') with a' += a*b'', b' += b*b''
 
 (this is summing over all derivations)
 
+
+==========
+
+is forward cost viterbi fine?  i.e. can i have items whose names ignore the lhs NT (look up predictions that i finish lazily / graph structured?)
-- 
cgit v1.2.3