summaryrefslogtreecommitdiff
path: root/report
diff options
context:
space:
mode:
authorgraehl <graehl@ec762483-ff6d-05da-a07a-a48fb63a330f>2010-08-04 02:12:45 +0000
committergraehl <graehl@ec762483-ff6d-05da-a07a-a48fb63a330f>2010-08-04 02:12:45 +0000
commit05680f52071bd06a748f028cadbaa15ac3c82d4e (patch)
treeb3ce7a3d86f9d4b74a5dbb722c33be0015a21b9a /report
parent9e294e17f6e14a531095150bd66b89b76dbe15c2 (diff)
slides
git-svn-id: https://ws10smt.googlecode.com/svn/trunk@474 ec762483-ff6d-05da-a07a-a48fb63a330f
Diffstat (limited to 'report')
-rwxr-xr-xreport/report.tex8
-rwxr-xr-xreport/ws10-graehl.pdfbin0 -> 557293 bytes
-rwxr-xr-xreport/ws10-graehl.pptxbin0 -> 254484 bytes
3 files changed, 4 insertions, 4 deletions
diff --git a/report/report.tex b/report/report.tex
index ca772fd2..1329d327 100755
--- a/report/report.tex
+++ b/report/report.tex
@@ -1,4 +1,4 @@
-\documentclass[11pt]{report}
+\documentclass[11pt]{report}
\usepackage{graphicx}
\usepackage{index}
\usepackage{varioref}
@@ -41,7 +41,7 @@ Chris Callison-Burch,
Trevor Cohn,
Chris Dyer,
Adam Lopez,\\
-\large
+\large
Jonathan Graehl,
Jonathan Weese,
Jan Botha,
@@ -52,7 +52,7 @@ Ziyuan Wang, \\
\normalsize
\maketitle
-
+
\section*{Abstract}
The last decade of research in Statistical Machine Translation (SMT) has seen rapid progress. The most successful methods have been based on synchronous context free grammars (SCFGs), which encode translational equivalences and license reordering between tokens in the source and target languages. Yet, while closely related language pairs can be translated with a high degree of precision now, the result for distant pairs is far from acceptable. In theory, however, the ``right'' SCFG is capable of handling most, if not all, structurally divergent language pairs. The 2010 Language Engineering Workshop {\emph Models of Synchronous Grammar Induction for SMT} had the goal to focus on the crucial practical aspects of acquiring such SCFGs from bilingual text. We started with existing algorithms for inducing unlabeled SCFGs (e.g. the popular Hiero model) and then used state-of-the-art unsupervised learning methods to refine the syntactic constituents used in the translation rules of the grammar.
@@ -76,7 +76,7 @@ We especially would like to thank Fred Jelinek for heading the Summer School eff
\item Trevor Cohn, Senior Researcher, University of Sheffield
\item Chris Dyer, Senior Researcher, Carnegie Mellon University
\item Adam Lopez, Senior Researcher, University of Edinburgh
-\item Jonathan Graehl, Senior Research, Information Sciences Institute, USC
+\item Jonathan Graehl, Senior Researcher, Information Sciences Institute, USC
\item Jan Botha, Graduate Student, University of Oxford
\item Vladimir Eidelman, Graduate Student, University of Maryland
\item Thuylinh Nguyen, Graduate Student, Carnegie Mellon University
diff --git a/report/ws10-graehl.pdf b/report/ws10-graehl.pdf
new file mode 100755
index 00000000..024d77c3
--- /dev/null
+++ b/report/ws10-graehl.pdf
Binary files differ
diff --git a/report/ws10-graehl.pptx b/report/ws10-graehl.pptx
new file mode 100755
index 00000000..ef125da5
--- /dev/null
+++ b/report/ws10-graehl.pptx
Binary files differ