mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2024-12-27 05:55:02 +03:00
Brooke: Added pdfs and updated report.tex and biblio.bib files. Included section on proposal for follow-up research.
git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@929 1f5c12ca-751b-0410-a591-d2e778427230
This commit is contained in:
parent
3c9e76d1de
commit
75d8695522
164
report/avm.sty
Normal file
164
report/avm.sty
Normal file
@ -0,0 +1,164 @@
|
||||
% avm.sty -- for attribute-value matrices -- v 1.00 mar 29, 1992
|
||||
% v 1.01 dec 6, 1993; v 1.02 jan 5, 2006
|
||||
% (c) 1992 christopher manning (manning@csli.stanford.edu) -- see avm-doc.tex
|
||||
|
||||
\newif\ifavmactive\newif\ifavmsorted\newif\ifavmlabeled
|
||||
\newif\ifavmcenter\newif\ifavmbottom
|
||||
\newif\ifavmbottomright\newif\ifavmtopleft\newif\ifavmtopright
|
||||
|
||||
\newdimen\avmdimen
|
||||
\newbox\avmboxone\newbox\avmboxthree
|
||||
|
||||
\def\avmoptions#1{\avmactivefalse\avmsortedfalse\avmlabeledfalse
|
||||
\avmcenterfalse\avmbottomfalse
|
||||
\avmbottomrightfalse\avmtopleftfalse\avmtoprightfalse
|
||||
\def\more{#1}\ifx\more\empty\else\avmjoptions#1,\@nil\fi}
|
||||
\def\avmjoptions#1,#2\@nil{\def\more{#2}\csname avm#1true\endcsname
|
||||
\ifx\more\empty\else\avmjoptions#2\@nil\fi}
|
||||
|
||||
|
||||
\def\avmfont#1{\def\avmjfont{#1}}
|
||||
\def\avmjfont{}
|
||||
|
||||
\def\avmvalfont#1{\def\avmjvalfont{#1}}
|
||||
\def\avmjvalfont{}
|
||||
|
||||
\def\avmsortfont#1{\def\avmjsortfont{#1}}
|
||||
\def\avmjsortfont{}
|
||||
|
||||
\def\avmhskip#1{\def\avmjhskip{#1}}
|
||||
\def\avmjhskip{1em}
|
||||
|
||||
\def\avmbskip#1{\def\avmjbskip{#1}}
|
||||
\def\avmjbskip{0em}
|
||||
|
||||
\def\avmvskip#1{\def\avmjvskip{#1}}
|
||||
\def\avmjvskip{0.385ex}%was .3875
|
||||
|
||||
|
||||
\def\avmjprolog#1{$\mskip-\thinmuskip
|
||||
\left#1\hskip\avmjbskip\vcenter\bgroup\vskip\avmjvskip
|
||||
\ialign\bgroup\avmjfont
|
||||
\strut ##\unskip\hfil
|
||||
&&\hskip\avmjhskip\avmjvalfont ##\unskip\hfil\cr}
|
||||
\def\avmjpostlog#1{\crcr\egroup\vskip\avmjvskip\egroup
|
||||
\hskip\avmjbskip\right#1\mskip-\thinmuskip$\ignorespaces}
|
||||
|
||||
|
||||
\def\avmjcatcode{\let\lparen=(\let\rparen=)\catcode`\[=13\catcode`\]=13
|
||||
\catcode`\<=13\catcode`\@=13\catcode`\(=13\catcode`\)=13
|
||||
\catcode`\>=13\catcode`\|=13}
|
||||
|
||||
{\avmjcatcode % new group: redefine above catcodes as active
|
||||
|
||||
\gdef\specialavm{\avmjcatcode
|
||||
\def({\avmjprolog\lparen}%
|
||||
\def){\avmjpostlog\rparen}%
|
||||
\def<{\avmjprolog\langle}%
|
||||
\def>{\avmjpostlog\rangle}%
|
||||
\ifavmsorted
|
||||
\def[##1{\setbox\avmboxthree=\hbox{\avmjsortfont##1\/}\setbox2=\hbox
|
||||
\bgroup\avmjprolog\lbrack}%
|
||||
\def]{\avmjpostlog\rbrack\egroup\avmjsort}%
|
||||
\else\ifavmlabeled
|
||||
\def[##1{\def\more{##1}\setbox2=\hbox\bgroup\avmjprolog[}%
|
||||
\def]{\avmjpostlog]\egroup\node{\more}{\box2}}%
|
||||
\else
|
||||
\def[{\avmjprolog\lbrack}%
|
||||
\def]{\avmjpostlog\rbrack}%
|
||||
\fi\fi
|
||||
%
|
||||
\def\<{$\langle$}\def\>{$\rangle$}%
|
||||
\def\({\lparen}\def\){\rparen}%
|
||||
\def\[{\lbrack}\def\]{\rbrack}%
|
||||
\def|{$\,\vert\,$}%
|
||||
\def@##1{\avmbox{##1}}%
|
||||
} % end defn of \specialavm
|
||||
} % restore active catcodes
|
||||
|
||||
|
||||
\long\def\avm{\begingroup
|
||||
\ifavmactive\specialavm
|
||||
\else
|
||||
\def\({\avmjprolog(}%
|
||||
\def\){\avmjpostlog)}%
|
||||
\def\<{\avmjprolog\langle}%
|
||||
\def\>{\avmjpostlog\rangle}%
|
||||
%
|
||||
\ifavmsorted
|
||||
\def\[##1{\setbox\avmboxthree=\hbox{\avmjsortfont##1\/}\setbox
|
||||
2=\hbox\bgroup\avmjprolog[}%
|
||||
\def\]{\avmjpostlog]\egroup\avmjsort}%
|
||||
\else\ifavmlabeled
|
||||
\def\[##1{\def\more{##1}\setbox2=\hbox\bgroup\avmjprolog[}%
|
||||
\def\]{\avmjpostlog]\egroup\node{\more}{\box2}}%
|
||||
\else
|
||||
\def\[{\avmjprolog[}%
|
||||
\def\]{\avmjpostlog]}%
|
||||
\fi\fi
|
||||
%
|
||||
\def\|{$\,\vert\,$}%
|
||||
\def\@##1{\avmbox{##1}}%
|
||||
\fi % end not active
|
||||
%
|
||||
\ifx\LaTeX\undefined\def\\{\cr}% running under TeX
|
||||
\else \ifx\@tabularcr\relax
|
||||
\def\\{\@arraycr} % fix for the Mainz array package
|
||||
\else
|
||||
\def\\{\@tabularcr}% Leverage off LaTeX's \\*[dimen] options
|
||||
\fi
|
||||
\fi
|
||||
\def\!{\node}%
|
||||
\long\def\avmjsort{\dimen2=\ht2\advance\dimen2 by -.25\baselineskip
|
||||
\global\dimen\avmdimen=\wd\avmboxthree
|
||||
\ifavmtopleft \raise\dimen2\llap{\box\avmboxthree}\box2%
|
||||
\else\ifavmtopright \box2\raise\dimen2\box\avmboxthree%
|
||||
\else\ifavmbottomright \box2\lower\dimen2\box\avmboxthree%
|
||||
\else \lower\dimen2\llap{\box\avmboxthree}\box2%
|
||||
\fi\fi\fi}%
|
||||
\long\def\sort##1##2{\setbox2=\hbox{##2}\setbox
|
||||
\avmboxthree=\hbox{\avmjsortfont##1\/}\dimen2=\ht2
|
||||
\advance\dimen2 by -.25\baselineskip
|
||||
\ifavmtopleft \raise\dimen2\box\avmboxthree\box2%
|
||||
\else\ifavmtopright \box2\raise\dimen2\box\avmboxthree%
|
||||
\else\ifavmbottomright \box2\lower\dimen2\box\avmboxthree%
|
||||
\else \lower\dimen2\box\avmboxthree\box2%
|
||||
\fi\fi\fi}%
|
||||
\long\def\osort##1##2{\setbox2=\hbox{##2}\setbox
|
||||
\avmboxthree=\hbox{\avmjsortfont ##1\/}\avmjsort}%
|
||||
\def\asort##1{\avmspan{\avmjsortfont ##1}\\}
|
||||
\def\avml{\avmjprolog.}%
|
||||
\def\avmr{\avmjpostlog.}%
|
||||
\def\avmb##1{\node{##1}{\lbrack\;\rbrack}}%
|
||||
\def\avmd##1{\node{##1}{---}}%
|
||||
\def\q##1{\ifx ##1\{$\lbrace$\else
|
||||
\ifx ##1\}$\rbrace$\else
|
||||
\ifx ##1<$\langle$\else
|
||||
\ifx ##1>$\rangle$\fi \fi \fi \fi}%
|
||||
\def\{{\avmjprolog\lbrace}%
|
||||
\def\}{\avmjpostlog\rbrace}%
|
||||
\def\;{\hskip\avmjhskip}%
|
||||
\def\avmspan##1{\multispan2\strut ##1\expandafter\hfil}%
|
||||
\avmjfont
|
||||
\openup\avmjvskip
|
||||
\setbox\avmboxone=\hbox\bgroup\ignorespaces
|
||||
} % end defn of \avm
|
||||
|
||||
|
||||
\def\endavm{\egroup\ifvmode\leavevmode\fi % this if is useful!
|
||||
\ifavmsorted\null\hskip\dimen\avmdimen\fi
|
||||
\ifavmcenter
|
||||
\box\avmboxone
|
||||
\else \ifavmbottom
|
||||
\lower.575\baselineskip\hbox{\vbox{\box\avmboxone\null}}%
|
||||
\else
|
||||
% the next bit is ripped off from Emma's \evnup in lingmacros.sty
|
||||
\dimen2=\ht\avmboxone\advance\dimen2 by -.725\baselineskip
|
||||
\lower\dimen2\box\avmboxone
|
||||
\fi \fi \endgroup}
|
||||
|
||||
|
||||
% based on TeXbook exercise 21.3
|
||||
\def\avmbox#1{\setbox2=\hbox{$\scriptstyle #1$}\lower.2ex\vbox{\hrule
|
||||
\hbox{\vrule\kern1.25pt
|
||||
\vbox{\kern1.25pt\box2\kern1.25pt}\kern1.25pt\vrule}\hrule}}
|
@ -4733,6 +4733,561 @@ strom\r{u} Pra\v{z}sk\'eho z\'avislostn\'{\i}ho korpusu}},
|
||||
year = "2001",
|
||||
}
|
||||
|
||||
@InProceedings{als:96,
|
||||
author = {Hiyan Alshawi},
|
||||
title = {Head automata and bilingual tiling: translation with minimal representations},
|
||||
booktitle = {ACL 96},
|
||||
year = {1996},
|
||||
}
|
||||
|
||||
@InProceedings{arukel:04,
|
||||
author = {Abhishek Arun and Frank Keller},
|
||||
title = {Lexicalization in crosslinguistic probabilistic parsing: the case of French},
|
||||
booktitle = {Proceedings of NIPS 2004},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@InProceedings{bar:04,
|
||||
author = {Peter Bartlett and Michael Collins and Ben Taskar and David McAllester},
|
||||
title = {Exponentiated gradient algorithms for large-margin structured classification},
|
||||
booktitle = {Proceedings of NIPS 2004},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@Article{bro:93,
|
||||
author = {Peter Brown and Stephen Della Pietra and Vincent Della Pietra and Robert Mercer},
|
||||
title = {The mathematics of statistical machine translation},
|
||||
journal = {Computational Linguistics},
|
||||
year = {1993},
|
||||
volume = {22},
|
||||
number = {1},
|
||||
pages = {39--69},
|
||||
}
|
||||
|
||||
@InProceedings{chajoh:05,
|
||||
author = {Eugene Charniak and Mark Johnson},
|
||||
title = {Coarse-to-fine {\it n}-best parsing and MaxEnt discriminative reranking},
|
||||
booktitle = {ACL 2005},
|
||||
year = {2005},
|
||||
address = {Ann Arbor, MI},
|
||||
}
|
||||
|
||||
@InProceedings{cha:01,
|
||||
author = {Eugene Charniak and Kevin Knight and Kenji Yamada},
|
||||
title = {Syntax-based language models for statistical machine translation},
|
||||
booktitle = {ACL '01},
|
||||
year = {2001},
|
||||
}
|
||||
|
||||
@InProceedings{chi:05,
|
||||
author = {David Chiang},
|
||||
title = {A hierarchical phrase-based model for statistical machine translation},
|
||||
booktitle = {ACL '05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
@InProceedings{chibik:02,
|
||||
author = {David Chiang and Daniel~M. Bikel},
|
||||
title = {Recovering latent information in treebanks},
|
||||
booktitle = {Proceedings of COLING-2002},
|
||||
year = {2002},
|
||||
}
|
||||
|
||||
@TechReport{civ:00,
|
||||
author = {Montserrat Civit Torruella},
|
||||
title = {Gu\'ia para la anotaci\'{o}n morfosint\'{a}ctica del corpus CLiC-TALP},
|
||||
institution = {X-Tract Working Paper, WP-00/06},
|
||||
year = {2000},
|
||||
}
|
||||
|
||||
@PhdThesis{col:99a,
|
||||
author = {Michael Collins},
|
||||
title = {Head-Driven Statistical Models for Natural Language Parsing},
|
||||
school = {University of Pennsylvania},
|
||||
year = {1999},
|
||||
}
|
||||
|
||||
@InProceedings{col:99b,
|
||||
author = {Michael Collins and Jan Hajic and Lance Ranshaw and Christoph Tillman},
|
||||
title = {A statistical parser for Czech},
|
||||
booktitle = {ACL 99},
|
||||
year = {1999},
|
||||
}
|
||||
|
||||
@InProceedings{col:02,
|
||||
author = {Michael Collins},
|
||||
title = {Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms},
|
||||
booktitle = {EMNLP 02},
|
||||
year = {2002},
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{colroa:04,
|
||||
author = {Michael Collins and Brian Roark},
|
||||
title = {Incremental parsing with the perceptron algorithm},
|
||||
booktitle = {ACL 04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@InProceedings{col:05,
|
||||
author = {Michael Collins and Philipp Koehn and Ivona Ku\v{c}erov\'{a}},
|
||||
title = {Clause restructuring for statistical machine translation},
|
||||
booktitle = {ACL 05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
@Article{colkoo:05,
|
||||
author = {Michael Collins and Terry Koo},
|
||||
title = {Discriminative Reranking for Natural Language Parsing},
|
||||
journal = {Computational Linguistics},
|
||||
year = {2005},
|
||||
volume = {31},
|
||||
number = {1},
|
||||
pages = {25--69},
|
||||
}
|
||||
|
||||
@Article{corvap:95,
|
||||
author = {Corinna Cortes and Vladimir Vapnik},
|
||||
title = {Support Vector Networks},
|
||||
journal = {Machine Learning},
|
||||
year = {1995},
|
||||
volume = {20},
|
||||
pages = {273--297},
|
||||
}
|
||||
|
||||
@InProceedings{daumar:05,
|
||||
author = {Hal Daum\'{e}~III and Daniel Marcu},
|
||||
title = {Learning as search optimization: approximate large margin methods for structured prediction},
|
||||
booktitle = {ICML '05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{dubkel:03,
|
||||
author = {Amit Dubey and Frank Keller},
|
||||
title = {Probabilistic parsing for German using sister-head dependencies},
|
||||
booktitle = {ACL '03},
|
||||
year = {2003},
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{dub:05,
|
||||
author = {Amit Dubey},
|
||||
title = {What to do when lexicalization fails: parsing German with suffix analysis and smoothing},
|
||||
booktitle = {ACL '05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
@InProceedings{eis:03,
|
||||
author = {Jason Eisner},
|
||||
title = {Learning non-isomorphic tree mappings for machine translation},
|
||||
booktitle = {ACL '03, Companion Volume},
|
||||
year = {2003},
|
||||
}
|
||||
|
||||
@Article{joh:98,
|
||||
author = {Mark Johnson},
|
||||
title = {PCFG Models of Linguistic Tree Representations},
|
||||
journal = {Computational Linguistics},
|
||||
year = {1998},
|
||||
volume = {24},
|
||||
number = {4},
|
||||
pages = {613--632},
|
||||
}
|
||||
|
||||
@Book{fra:02,
|
||||
author = {Robert Frank},
|
||||
title = {Phrase Structure Composition and Syntactic Dependencies},
|
||||
publisher = {MIT Press},
|
||||
year = {2002},
|
||||
address = {Cambridge, MA},
|
||||
}
|
||||
|
||||
@InProceedings{gal:04,
|
||||
author = {Michel Galley and Mark Hopkins and Kevin Knight and Daniel Marcu},
|
||||
title = {What's in a translation rule?},
|
||||
booktitle = {HLT-NAACL '04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{gil:03,
|
||||
author = {Daniel Gildea},
|
||||
title = {Loosely tree-based alignment for machine translation},
|
||||
booktitle = {ACL '03},
|
||||
year = {2003},
|
||||
}
|
||||
|
||||
@InProceedings{grakni:04,
|
||||
author = {Jonathan Graehl and Kevin Knight},
|
||||
title = {Training tree transducers},
|
||||
booktitle = {NAACL-HLT 04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@Book{jos:85,
|
||||
author = {Aravind Joshi},
|
||||
title = {How much context-sensitivity is necessary for characterizing structural descriptions -- tree-adjoining grammar},
|
||||
publisher = {Cambridge University Press},
|
||||
year = {1985},
|
||||
}
|
||||
|
||||
@InProceedings{koe:03,
|
||||
author = {Philipp Koehn and Franz Josef Och and Daniel Marcu},
|
||||
title = {Statistical phrase based translation},
|
||||
booktitle = {HLT-NAACL '03},
|
||||
year = {2003},
|
||||
}
|
||||
|
||||
@InProceedings{koe:05,
|
||||
author = {Philipp Koehn},
|
||||
title = {Europarl: A parallel corpus for statistical machine translation},
|
||||
booktitle = {MT Summit 05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
@InProceedings{levman:03,
|
||||
author = {Roger Levy and Christopher Manning},
|
||||
title = {Is it harder to parse Chinese, or the Chinese Treebank?},
|
||||
booktitle = {ACL '03},
|
||||
year = {2003},
|
||||
}
|
||||
|
||||
@InProceedings{mel:04,
|
||||
author = {I. Dan Melamed},
|
||||
title = {Statistical machine translation by parsing},
|
||||
booktitle = {ACL '04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@InProceedings{mor:00,
|
||||
author = {Antonio Moreno and Ralph Grishman and Susana L\'{o}pez and Fernando S\'{a}nchez and Satoshi Sekine},
|
||||
title = {A treebank of Spanish and its application to parsing},
|
||||
booktitle = {The Proceedings of the Workshop on Using Evaluation within HLT Programs: Results and Trends},
|
||||
year = {2000},
|
||||
address = {Athens, Greece},
|
||||
}
|
||||
|
||||
@InProceedings{nav:03,
|
||||
author = {Borja Navarro and Montserrat Civit and Ma. Ant\`{o}nia Mart\'{i} and Raquel Marcos and Bel\'{e}n Fern\'{a}ndez},
|
||||
title = {Syntactic, semantic and pragmatic annotation in Cast3LB},
|
||||
booktitle = {Shallow Processing of Large Corpora (SProLaC), a Workshop of Corpus Linguistics},
|
||||
year = {2003},
|
||||
address = {Lancaster, UK},
|
||||
}
|
||||
|
||||
@InProceedings{och:04,
|
||||
author = {F. J. Och and D. Gildea and S. Khudanpur and A. Sarkar and K. Yamada and A. Fraser and S. Kumar and L. Shen and D. Smith and K. Eng and V. Jain and Z. Jin and D. Radev},
|
||||
title = {A smorgasbord of features for statistical machine translation},
|
||||
booktitle = {HLT/NAACL '04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@Article{ochney:04,
|
||||
author = {Franz Josef Och and Hermann Ney},
|
||||
title = {The alignment template approach to statistical machine translation},
|
||||
journal = {Computational Linguistics},
|
||||
year = {2004},
|
||||
volume = {30},
|
||||
number = {4},
|
||||
pages = {417--449},
|
||||
}
|
||||
|
||||
@Article{ochney:03,
|
||||
author = {Franz Josef Och and Hermann Ney},
|
||||
title = {A systematic comparison of various statistical alignment models},
|
||||
journal = {Computational Linguistics},
|
||||
year = {2003},
|
||||
volume = {29},
|
||||
number = {1},
|
||||
pages = {19--51},
|
||||
}
|
||||
|
||||
@InProceedings{qui:05,
|
||||
author = {Chris Quirk and Arul Menezes and Colin Cherry},
|
||||
title = {Dependency tree translation: syntactically informed phrasal SMT},
|
||||
booktitle = {EACL '05},
|
||||
year = {2005},
|
||||
}
|
||||
|
||||
@InProceedings{riemax:06,
|
||||
author = {Stefan Riezler and John Maxwell},
|
||||
title = {Grammatical machine translation},
|
||||
booktitle = {NLT-NAACL '06},
|
||||
year = {2006},
|
||||
}
|
||||
|
||||
@InProceedings{shi:04,
|
||||
author = {Stuart Shieber},
|
||||
title = {Synchronous grammars as tree transducers},
|
||||
booktitle = {Proceedings of the Seventh International Workshop on Tree Adjoining Grammar and Related Formalisms},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@InProceedings{shisch:90,
|
||||
author = {Stuart Shieber and Yves Schabes},
|
||||
title = {Synchronous tree-adjoining grammars},
|
||||
booktitle = {Proceedings of the 13th International Conference on Computational Linguistics},
|
||||
year = {1990},
|
||||
}
|
||||
|
||||
@Article{wu:97,
|
||||
author = {Dekai Wu},
|
||||
title = {Stochastic inversion transduction grammars and bilingual parsing of parallel corpora},
|
||||
journal = {Computational Linguistics},
|
||||
year = {1997},
|
||||
volume = {23},
|
||||
number = {3},
|
||||
pages = {377--403},
|
||||
}
|
||||
|
||||
@InProceedings{xiamcc:04,
|
||||
author = {Fei Xia and Michael McCord},
|
||||
title = { Improving a statistical MT system with automatically learned rewrite patterns},
|
||||
booktitle = {COLING '04},
|
||||
year = {2004},
|
||||
}
|
||||
|
||||
@InProceedings{yamkni:01,
|
||||
author = {Kenji Yamada and Kevin Knight},
|
||||
title = {A syntax-based statistical translation model},
|
||||
booktitle = {ACL '01},
|
||||
year = {2001},
|
||||
}
|
||||
|
||||
@InProceedings{pop:06,
|
||||
author = {Maja Popovi\'{c} and Adri\`{a} de Gispert and Deepa Gupta and Patrik Lambert and Hermann Ney and Jos\'{e} B. Mari\~{n}o and Marcello Federico and Rafael Banchs},
|
||||
title = {Morph-Syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output},
|
||||
booktitle = {Proceedings of the Workshop on Statistical Machine Translation},
|
||||
pages = {1---6},
|
||||
year = {2006},
|
||||
address = {New York City, NY},
|
||||
month = {June},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {Spanish<->English, measuring errors in (1) reordering of e.g., nouns and adjectives and (2) inflection of e.g., verbs by looking at WER vs PER vs BLEU of full and inflected forms. Error rates are higher for into Spanish than into English. }
|
||||
}
|
||||
|
||||
|
||||
|
||||
@InProceedings{elkofl:06,
|
||||
author = {\dot{I}lknur Durgar El-Kahlout and Kemal Oflazer},
|
||||
title = {Initial Explorations in English to Turkish Statistical Machine Translation},
|
||||
booktitle = {Proceedings of the Workshop on Statistical Machine Translation},
|
||||
pages = {7---14},
|
||||
year = {2006},
|
||||
address = {New York City, NY},
|
||||
month = {June},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {Turkish-English; Turkish is an agglutinative language, meaning that words are formed by gluing morphemes onto roots. This presents a challenge to SMT, both for the word alignment subtask as well as reordering. By breaking up Turkish and English words into morphemic subcomponents and doing some further filtering for "appropriateness" of morphemic agglutination with predicted root forms, the authors are able to get a small gain in BLEU (1.5-2 points). However, the baseline score is quite low (~7.5 BLEU), and even the prediction of root forms is poor. Is the problem lack of data? (only 20K training examples). The authors suggest that there is a also a significant amount of reordering that messes with the word alignment process.}
|
||||
}
|
||||
|
||||
@InProceedings{zenney:03,
|
||||
author = {Richard Zens and Hermann Ney},
|
||||
title = {A Comparative Study on Reordering Constraints in Statistical Machine Translation},
|
||||
booktitle = {Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics},
|
||||
pages = {144--151},
|
||||
year = {2003},
|
||||
month = {July},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{ochney:00,
|
||||
author = {Franz Josef Och and Hermann Ney},
|
||||
title = {A Comparison of Alignment Models for Statistical Machine Translation},
|
||||
booktitle = {COLING '00: The 18th International Conference on Computational Linguistics},
|
||||
pages = {1086--1090},
|
||||
year = {2000},
|
||||
address = {Saarbrücken, Germany},
|
||||
month = {July},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{ochney:02,
|
||||
author = {Franz Josef Och and Hermann Ney},
|
||||
title = {Discriminative Training and Maximum Entropy Models for Statistical Machine Translation},
|
||||
booktitle = {ACL 2002: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics},
|
||||
pages = {295--302},
|
||||
year = {2002},
|
||||
address = {Philadelphia, PA},
|
||||
month = {July},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{koe:04,
|
||||
author = {Philipp Koehn},
|
||||
title = {Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models},
|
||||
booktitle = {Proceedings of the Sixth Conference of the Association for Machine Translation in the Americas},
|
||||
pages = {115--124},
|
||||
year = {2004},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
|
||||
|
||||
@InProceedings{och:03,
|
||||
author = {Franz Josef Och},
|
||||
title = {Minimum Error Rate Training in Statistical Machine Translation},
|
||||
booktitle = {Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics},
|
||||
pages = {160--167},
|
||||
year = {2003},
|
||||
month = {July},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{pap:02,
|
||||
author = {Kishore Papineni and Salim Roukos and Todd Ward and Wei-Jing Zhu},
|
||||
title = {BLEU: A Method for Automatic Evaluation of Machine Translation},
|
||||
booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics},
|
||||
pages = {311--318},
|
||||
year = {2002},
|
||||
address = {Philadelphia, PA},
|
||||
month = {July},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{zha:04,
|
||||
author = {Ying Zhang and Stephan Vogel and Alex Waibel},
|
||||
title = {Interpreting BLEU/NIST Scores: How Much Improvement Do We Need to Have a Better System?},
|
||||
booktitle = {Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC)},
|
||||
pages = {2051--2054},
|
||||
year = {2004},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{cal:06,
|
||||
author = {Chris Callison-Burch and Miles Osborne and Philipp Koehn},
|
||||
title = {Re-evaluating the Role of BLEU in Machine Translation Research},
|
||||
booktitle = {Proceedings of EACL-2006},
|
||||
year = {2006},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{cowcol:05,
|
||||
author = {Brooke Cowan and Michael Collins},
|
||||
title = {Morphology and Reranking for the Statistical Parsing of Spanish},
|
||||
booktitle = {Proceedings of the Joint Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT/EMNLP)},
|
||||
year = {2005},
|
||||
address = {Vancouver, BC, Canada},
|
||||
month = {October},
|
||||
}
|
||||
|
||||
@Book{zag:02,
|
||||
author = {Karen Zagona},
|
||||
title = {The Syntax of Spanish},
|
||||
publisher = {Cambridge University Press},
|
||||
year = {2002},
|
||||
address = {Cambridge, UK},
|
||||
}
|
||||
|
||||
@InProceedings{kub:06,
|
||||
author = {Sandra K\"{u}bler and Erhard~W. Hinrichs and Wolfgang Maier},
|
||||
title = {Is it Really that Difficult to Parse German?},
|
||||
booktitle = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)},
|
||||
pages = {111--119},
|
||||
year = {2006},
|
||||
address = {Sydney, Australia},
|
||||
month = {July},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
|
||||
@InProceedings{quicor:06,
|
||||
author = {Chris Quirk and Simon Corston-Oliver},
|
||||
title = {The impact of parse quality of syntactically-informed statistical machine translation},
|
||||
booktitle = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)},
|
||||
pages = {62--69},
|
||||
year = {2006},
|
||||
address = {Sydney, Australia},
|
||||
month = {July},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{sku:97,
|
||||
author = {Wojciech Skut and Brigitte Krenn and Thorsten Brants and Hans Uszkoreit},
|
||||
title = {An annotation scheme for free word order languages},
|
||||
booktitle = {Proceedings of ANLP 1997},
|
||||
year = {1997},
|
||||
address = {Washington, D.C.},
|
||||
annote = {Negra treebank}
|
||||
}
|
||||
|
||||
@Misc{tel:05,
|
||||
author = {Heike Telljohann and Erhard~W. Hinrichs and Sandra K\"{u}bler and Heike Zinsmeister},
|
||||
title = {Stylebook for the T\"{u}bingen Treebank of Written German (T\"{u}Ba-D/Z)},
|
||||
howpublished = {Seminar f\"{u}r Sprachwissenschaft, Universit\"{a}t T\"{u}bingen, German},
|
||||
year = {2005},
|
||||
annote = {T\"{u}Ba-D/Z treebank}
|
||||
}
|
||||
|
||||
@InProceedings{cow:06,
|
||||
author = {Brooke Cowan and Ivona Ku\v{c}erov\'{a} and Michael Collins},
|
||||
title = {A Discriminative Model for Tree-to-Tree Translation},
|
||||
booktitle = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)},
|
||||
pages = {232--241},
|
||||
year = {2006},
|
||||
address = {Sydney, Australia},
|
||||
month = {July},
|
||||
organization = {Association for Computational Linguistics},
|
||||
}
|
||||
|
||||
@Article{kni:99,
|
||||
author = {Kevin Knight},
|
||||
title = {Decoding complexity in word-replacement translation models},
|
||||
journal = {Computational Linguistics},
|
||||
year = {1999},
|
||||
volume = {24},
|
||||
number = {4},
|
||||
pages = {607--615},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@InProceedings{lia:06,
|
||||
author = {Percy Liang and Alexandre Bouchard-C\^{o}t\'{e} and Dan Klein and Ben Taskar},
|
||||
title = {An End-to-End Discriminative Approach to Machine Translation},
|
||||
booktitle = {ACL 2006},
|
||||
year = {2006},
|
||||
organization = {Association for Computational Linguistics},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@Article{bar:51,
|
||||
author = {Yehoshua Bar-Hillel},
|
||||
title = {The Present State of Research on Mechanical Translation},
|
||||
journal = {American Documentation},
|
||||
year = {1951},
|
||||
volume = {2},
|
||||
number = {4},
|
||||
pages = {229--237},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@Book{haegue:99,
|
||||
author = {Liliane Haegeman and Jacqueline Gu\'{e}ron},
|
||||
title = {English Grammar: A Generative Perspective},
|
||||
publisher = {Blackwell Publishers Ltd.},
|
||||
year = {1999},
|
||||
address = {Oxford, UK},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
@Article{moh:97,
|
||||
author = {Mehryar Mohri},
|
||||
title = {Finite-State Transducers in Language and Speech Processing},
|
||||
journal = {Computational Linguistics},
|
||||
year = {1997},
|
||||
volume = {23},
|
||||
number = {2},
|
||||
annote = {}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
%article
|
||||
% An article from a journal or magazine. Required fields: author, title,
|
||||
|
BIN
report/brooke-AEP.pdf
Normal file
BIN
report/brooke-AEP.pdf
Normal file
Binary file not shown.
BIN
report/brooke-basicorder.pdf
Normal file
BIN
report/brooke-basicorder.pdf
Normal file
Binary file not shown.
BIN
report/brooke-freeorder.pdf
Normal file
BIN
report/brooke-freeorder.pdf
Normal file
Binary file not shown.
BIN
report/brooke-localreorder.pdf
Normal file
BIN
report/brooke-localreorder.pdf
Normal file
Binary file not shown.
BIN
report/brooke-modifiedinput2.pdf
Normal file
BIN
report/brooke-modifiedinput2.pdf
Normal file
Binary file not shown.
BIN
report/brooke-movement.pdf
Normal file
BIN
report/brooke-movement.pdf
Normal file
Binary file not shown.
1334
report/report.tex
1334
report/report.tex
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user