From 2b8a391ccd64fddaa990a41c66c30d88b2331ad3 Mon Sep 17 00:00:00 2001
From: desaicwtf <desaicwtf@ec762483-ff6d-05da-a07a-a48fb63a330f>
Date: Tue, 17 Aug 2010 10:43:20 +0000
Subject: git-svn-id: https://ws10smt.googlecode.com/svn/trunk@570
ec762483-ff6d-05da-a07a-a48fb63a330f
---
report/pr-clustering/posterior.tex | 41 ++++++++++++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
(limited to 'report/pr-clustering')
diff --git a/report/pr-clustering/posterior.tex b/report/pr-clustering/posterior.tex
index 7597c8e1..ebb05211 100644
--- a/report/pr-clustering/posterior.tex
+++ b/report/pr-clustering/posterior.tex
@@ -221,4 +221,45 @@ with an intrinsic evaluation of clustering quality
by comparing against a supervised CFG parser trained on the
tree bank.
+We are mainly working on Urdu-English language pair.
+Urdu has very
+different word ordering from English.
+This leaves us room for improvement over
+phrase-based systems.
+Here in Table \ref{tab:results}
+we show BLEU scores as well as
+conditional entropy for each of the models above
+on Urdu data. Conditional entropy is computed
+as the entropy of ``gold'' labelling given
+the predicted clustering. ``Gold'' labelling
+distribution
+is obtained from Collins parser
+trained on Penn Treebank. Since not
+all phrases are constituents, we ignored
+phrases that don't correspond any constituents.
+\begin{table}[h]
+ \centering
+ \begin{tabular}{ |*{3}{c|} }
+ \hline
+ model & BLEU & H(Gold$|$Predicted)\\
+ \hline
+ hiero & 21.1 & 5.77\\
+ hiero+POS & & \\
+ SAMT & & \\
+ EM & & \\
+ pr100 & & \\
+ agree-language & & \\
+ agree direction & &\\
+ non-parametric & & \\
+ \hline
+ \end{tabular}
+ \caption
+ {Evaluation of PR models.
+ Left column shows BLEU scores
+ through the translation pipeline.
+ Right columns shows conditional entropy
+ of the
+ }
+ \label{tab:results}
+\end{table}
--
cgit v1.2.3