2 files changed, 20 insertions, 4 deletions

diff --git a/report/biblio.bib b/report/biblio.bib
index 8fa74c6d..261e965f 100644
--- a/report/biblio.bib
+++ b/report/biblio.bib
@@ -1,5 +1,11 @@
 @string{acl-1989 = {27th Annual Meeting of the Association for Computational Linguistics (ACL-1989)}}

@string{acl-1989-address = {Vancouver, British Columbia, Canada}}

@string{acl-1995 = {33rd Annual Meeting of the Association for Computational Linguistics (ACL-1995)}}

@string{acl-1995-address = {Cambridge, Massachusetts}}

@string{acl-1996 = {34rd Annual Meeting of the Association for Computational Linguistics (ACL-1996)}}

@string{acl-1996-address = {Santa Cruz, California}}

@string{acl-1997 = {35th Annual Meeting of the Association for Computational Linguistics (ACL-1997)}}

@string{acl-1997-address = {Madrid, Spain}}

@string{acl-1998 = {36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (ACL-CoLing-1998)}}

@string{acl-1998-address = {Montreal, Canada}}

@string{acl-1999 = {Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL)}}

@string{acl-1999-address = {College Park, Maryland}}

@string{acl-2000 = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-2000)}}

@string{acl-2000-address = {Hong Kong}}

@string{acl-2001 = {Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-2001)}}

@string{acl-2001-address = {Toulouse, France}}

@string{acl-2002 = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-2002)}}

@string{acl-2002-address = {Philadelphia, Pennsylvania}}

@string{acl-2003 = {Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003)}}

@string{acl-2003-address = {Sapporo, Japan}}

@string{acl-2004 = {Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-2004)}}

@string{acl-2004-address = {Barcelona, Spain}}

@string{acl-2005 = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005)}}

@string{acl-2005-address = {Ann Arbor, Michigan}}

@string{acl-2006 = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (ACL-CoLing-2006)}}

@string{acl-2006-address = {Sydney, Australia}}

@string{acl-2007 = {Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL-2007)}}

@string{acl-2007-address = {Prague, Czech Republic}}

@string{acl-2008 = {Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies}}

@string{acl-2008-address = {Colmbus, Ohio}}

@string{acl-2009-address = {Singapore}}

@string{amta-2002 = {Proceedings of the 5th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2002)}}

@string{amta-2002-address = {Tiburon, California}}

@string{amta-2004 = {Proceedings of the 6th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2004)}}

@string{amta-2004-address = {Washington DC}}

@string{amta-2006 = {Proceedings of the 7th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2006)}}

@string{amta-2006-address = {Cambridge, Massachusetts}}

@string{amta-2008 = {Proceedings of the 8th Biennial Conference of the Association for Machine Translation in the Americas (AMTA-2008)}}

@string{amta-2008-address = {Honolulu, Hawaii}}

@string{coling-2008 = {Proceedings of the 22nd International Conference on Computational Linguistics (COLING-2008)}}

@string{coling-2008-address = {Manchester, England}}

@string{eacl-1989 = {4th Conference of the European Chapter of the Association for Computational Linguistics (EACL-1989)}}

@string{eacl-1989-address = {Manchester, England}}

@string{eacl-2003 = {10th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2003)}}

@string{eacl-2003-address = {Budapest, Hungary}}

@string{eacl-2006 = {11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2006)}}

@string{eacl-2006-address = {Trento, Italy}}

@string{eacl-2009 = {12th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2009)}}

@string{eacl-2009-address = {Athens, Greece}}

@string{emnlp-2000 = {2000 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora}}

@string{emnlp-2000-address = {Hong Kong}}

@string{emnlp-2001 = {Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing (EMNLP-2001)}}

@string{emnlp-2001-address = {Pittsburgh, Pennsylvania}}

@string{emnlp-2002 = {Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP-2002)}}

@string{emnlp-2002-address = {Philadelphia, Pennsylvania}}

@string{emnlp-2003 = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing (EMNLP-2003)}}

@string{emnlp-2003-address = {Sapporo, Japan}}

@string{emnlp-2004 = {Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-2004)}}

@string{emnlp-2004-address = {Barcelona, Spain}}

@string{emnlp-2005 = {Proceedings of the 2005 Conference on Empirical Methods in Natural Language Processing (EMNLP-2005)}}

@string{emnlp-2005-address = {Vancouver, British Columbia., Canada}}

@string{emnlp-2006 = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP-2006)}}

@string{emnlp-2006-address = {Sydney, Australia}}

@string{emnlp-2007 = {Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)}}

@string{emnlp-2007-address = {Prague, Czech Republic}}

@string{emnlp-2008 = {Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP-2008)}}

@string{emnlp-2008-address = {Honolulu, Hawaii}}

@string{emnlp-2009 = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP-2009)}}

@string{emnlp-2009-address = {Singapore}}

@string{hlt-2002 = {Proceedings of Second International Conference on Human Language Technology Research (HLT-02)}}

@string{hlt-2002-address = {San Diego}}

@string{hlt-naacl-2003 = {Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2003)}}

@string{hlt-naacl-2003-address = {Edmonton, Alberta}}

@string{hlt-naacl-2004 = {Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2004)}}

@string{hlt-naacl-2004-address = {Boston, Massachusetts}}

@string{hlt-naacl-2006 = {Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2006)}}

@string{hlt-naacl-2006-address = {New York, New York}}

@string{hlt-naacl-2007 = {Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2007)}}

@string{hlt-naacl-2007-address = {Rochester, New York}}

@string{hlt-naacl-2009-address = {Boulder, Colorado}}

@string{iwpt = {Proceedings of the International Workshop on Parsing Technologies}}

@string{iwpt-2005-address = {Vancouver, BC, Canada}}

@string{iwslt = {Proceedings of the International Workshop on Spoken Language Technology}}

@string{kdd = {Proceeding of the ACM SIGKDD international conference on Knowledge discovery and data mining}}

@string{kdd-2008-address = {New York}}

@string{mt-summit-9-address = {New Orleans, Louisiana}}

@string{naacl-2001 = {Second Meeting of the North American Chapter of the Association for Computational Linguistics}}

@string{naacl-2001-address = {Pittsburgh, Pennsylvania}}

@string{wmt = {Proceedings of the Workshop on Statistical Machine Translation}}


-
@inproceedings{Chiang2005,
	Address = acl-2005-address,
	Author = {David Chiang},
	Booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005)}},
	Title = {A Hierarchical Phrase-based Model for Statistical Machine Translation},
	Year = {2005}}
+
+@inproceedings{Chiang2005,
+	address = acl-2005-address,
+	author = {David Chiang},
+	booktitle = {Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005)},
+	title = {A Hierarchical Phrase-based Model for Statistical Machine Translation},
+	year = {2005}}
 
 
@inproceedings{Koehn2003,
	Address = hlt-naacl-2003-address,
	Author = {Philipp Koehn and  Franz Josef Och and Daniel Marcu},
	Booktitle = {{Proceedings of the Human Language Technology Conference of the North American chapter of the Association for Computational Linguistics (HLT/NAACL-2003)}},
	Title = {Statistical Phrase-Based Translation},
	Url = {http://www.isi.edu/~koehn/publications/phrase2003.pdf},
	Year = {2003}}
 
@@ -207,3 +213,13 @@ title = {{Unsupervised models for morpheme segmentation and morphology learning}
 volume = {4},
 year = {2007}
 }
+
+@article{harris:54,
+author = {Zellig Harris},
+year = 1954,
+title = {Distributional structure},
+journal = {Word}, 
+volume = 10,
+number = 23,
+pages = {146--162}
+}
diff --git a/report/setup.tex b/report/setup.tex
index 8fccf1b3..b4f3f07d 100644
--- a/report/setup.tex
+++ b/report/setup.tex
@@ -1,8 +1,8 @@
 \chapter{Experimental Setup}
 
-Our approach is based upon the popular and influential Hiero system \cite{chiang07} which uses a synchronous context free grammar (SCFG) to model translation. 
+Our approach is based upon the popular and influential Hiero system \citep{chiang:2007} which uses a synchronous context free grammar (SCFG) to model translation. 
 This translation system uses only a single non-terminal symbol and therefore the system is inherently stateless. 
-However, we know that using a richer set of non-terminals can greatly improve translation, as evidenced by the improvments obtained by SAMT system \cite{samt} which augments a Hiero-style SCFG model with syntactic labels.
+However, we know that using a richer set of non-terminals can greatly improve translation, as evidenced by the improvments obtained by SAMT system \citep{samt} which augments a Hiero-style SCFG model with syntactic labels.
 This is best explained in terms of the generalisation capability: a single category grammar can create all manner of string-pairs, the majority of which are nonsensical and agrammatical, while a model with syntactic categories inherently limits the sets of string pairs to those which are grammatical (largely).
 This can be seen from the following example rules, showing how rules can be combined to arrive at ungrammatical string pairs.
 \begin{align}
@@ -24,7 +24,7 @@ This allows our approach to be more easily ported to work for translating a vari
 \section{Distributional Hypothesis}
 
 Underlying most models of grammar induction is the distributional hypothesis. This theory states that
-``words that occur in the same contexts tend to have similar meaning'' \cite{harris:54}. Although phrased in terms of semantics, the distributional hypothesis applies equally to syntax, that is, words that can be substituted for one another most often share the same syntactic category (in general, semantics implies syntax). This is evidenced by the wide-spread use of the substitution test in theories of syntax to determine the constituency and syntactic category of a word or phrase.
+``words that occur in the same contexts tend to have similar meaning'' \citep{harris:54}. Although phrased in terms of semantics, the distributional hypothesis applies equally to syntax, that is, words that can be substituted for one another most often share the same syntactic category (in general, semantics implies syntax). This is evidenced by the wide-spread use of the substitution test in theories of syntax to determine the constituency and syntactic category of a word or phrase.
 
 The majority of work on monolingual grammar induction has used some notion of context to inform the induced categories. This is best seen in the work of Alex Clark who uses the context surrounding a phrase to determine its category, and in Dan Klein's work, which uses context to determine constituency. In this project we follow the lead of these earlier works on monolingual grammar induction by using context to inform our clustering of words and phrases, such that words that appear in similar contexts are assigned to the same cluster. We expect that this clustering should bear a strong resemblance to the underlying syntax and, to some extent, the semantics of the language, and therefore improve translation accuracy.