marian/paper/references.bib

@inproceedings{pouliquen_un_2012,
    author = {Bruno Pouliquen and Christophe Mazenc and Cecilia Elizalde and Jose Garcia-Verdugo},
    booktitle = {16th Annual Conference of the European Association for Machine Translation (EAMT 2012)},
    title = {Statistical Machine Translation prototype using {UN} parallel documents},
    year = {2012},
    pages = {12--19},
    address= {Trento, Italy}
}

@article{DBLP:journals/corr/Junczys-Dowmunt16,
  author    = {Marcin Junczys{-}Dowmunt and
               Roman Grundkiewicz},
  title     = {Log-linear Combinations of Monolingual and Bilingual Neural Machine
               Translation Models for Automatic Post-Editing},
  journal   = {CoRR},
  volume    = {abs/1605.04800},
  year      = {2016},
  url       = {http://arxiv.org/abs/1605.04800},
  timestamp = {Wed, 01 Jun 2016 15:51:08 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/Junczys-Dowmunt16},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}


@inproceedings{Knowles,
  author = {Rebecca Knowles and Philipp Koehn},
  title = {Neural Interactive Translation Prediction},
  year = {2016},
  month = {October},
  booktitle = {Proceedings of AMTA 2016},
  address = {Austin, USA}
}


@article{DBLP:journals/corr/BahdanauCB14,
  author    = {Dzmitry Bahdanau and
               Kyunghyun Cho and
               Yoshua Bengio},
  title     = {Neural Machine Translation by Jointly Learning to Align and Translate},
  journal   = {CoRR},
  volume    = {abs/1409.0473},
  year      = {2014},
  url       = {http://arxiv.org/abs/1409.0473},
  timestamp = {Wed, 01 Oct 2014 15:00:04 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/BahdanauCB14},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

@article{DBLP:journals/corr/SennrichHB15,
  author    = {Rico Sennrich and
               Barry Haddow and
               Alexandra Birch},
  title     = {Neural Machine Translation of Rare Words with Subword Units},
  journal   = {CoRR},
  volume    = {abs/1508.07909},
  year      = {2015},
  url       = {http://arxiv.org/abs/1508.07909},
  timestamp = {Tue, 01 Sep 2015 14:42:40 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/SennrichHB15},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}


@InProceedings{ZIEMSKI16.1195,
  author = {Micha\l{} Ziemski and Marcin Junczys-Dowmunt and Bruno Pouliquen},
  title = {The United Nations Parallel Corpus v1.0},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
  year = {2016},
  month = {may},
  date = {23-28},
  location = {Portorož, Slovenia},
  editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Sara Goggi and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  address = {Paris, France},
  isbn = {978-2-9517408-9-1},
  language = {english}
 } 

 @inproceedings{DBLP:conf/icml/PascanuMB13,
    address = ", Atlanta, GA, USA",
    author = "Pascanu, Razvan and Mikolov, Tomas and Bengio, Yoshua",
    bibsource = "dblp computer science bibliography, http://dblp.org",
    booktitle = "{Proceedings of the 30th International Conference on Machine Learning, {ICML} 2013}",
    pages = "1310--1318",
    timestamp = "Thu, 11 Sep 2014 07:28:55 +0200",
    title = "{On the difficulty of training recurrent neural networks}",
    year = "2013"
}

@article{DBLP:journals/corr/abs-1212-5701,
    author = "Zeiler, Matthew D.",
    bibsource = "dblp computer science bibliography, http://dblp.org",
    biburl = "http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1212-5701",
    journal = "CoRR",
    timestamp = "Wed, 02 Jan 2013 09:49:04 +0100",
    title = "{{ADADELTA:} An Adaptive Learning Rate Method}",
    url = "http://arxiv.org/abs/1212.5701",
    volume = "abs/1212.5701",
    year = "2012"
}


@inproceedings{DBLP:conf/wmt/SennrichHB16,
  author    = {Rico Sennrich and
               Barry Haddow and
               Alexandra Birch},
  title     = {Edinburgh Neural Machine Translation Systems for {WMT} 16},
  booktitle = {Proceedings of the First Conference on Machine Translation, {WMT}
               2016, colocated with {ACL} 2016, August 11-12, Berlin, Germany},
  pages     = {371--376},
  year      = {2016},
  crossref  = {DBLP:conf/wmt/2016},
  url       = {http://aclweb.org/anthology/W/W16/W16-2323.pdf},
  timestamp = {Wed, 14 Sep 2016 08:53:03 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/conf/wmt/SennrichHB16},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}

@proceedings{DBLP:conf/wmt/2016,
  title     = {Proceedings of the First Conference on Machine Translation, {WMT}
               2016, colocated with {ACL} 2016, August 11-12, Berlin, Germany},
  publisher = {The Association for Computer Linguistics},
  year      = {2016},
  url       = {http://aclweb.org/anthology/W/W16/},
  timestamp = {Wed, 14 Sep 2016 08:53:03 +0200},
  biburl    = {http://dblp.uni-trier.de/rec/bib/conf/wmt/2016},
  bibsource = {dblp computer science bibliography, http://dblp.org}
}


@inproceedings{citeulike:7010210,
    author = {Varga, D. and N\'{e}meth, L. and Hal\'{a}csy, P. and Kornai, A. and Tr\'{o}n, V. and Nagy, V.},
    booktitle = {Recent Advances in Natural Language Processing (RANLP 2005)},
    citeulike-article-id = {7010210},
    pages = {590--596},
    posted-at = {2010-04-12 16:16:59},
    priority = {2},
    title = {Parallel corpora for medium density languages},
    year = {2005}
}

@article{google,
  author    = {Yonghui Wu and Mike Schuster and Zhifeng Chen and Quoc V. Le and Mohammad Norouzi and Wolfgang Macherey and Maxim Krikun and Yuan Cao and Qin Gao and Klaus Macherey and Jeff Klingner and Apurva Shah and Melvin Johnson and Xiaobing Liu and Łukasz Kaiser and Stephan Gouws and Yoshikiyo Kato and Taku Kudo and Hideto Kazawa and Keith Stevens and George Kurian and Nishant Patil and Wei Wang and Cliff Young and Jason Smith and Jason Riesa and Alex Rudnick and Oriol Vinyals and Greg Corrado and Macduff Hughes and Jeffrey Dean},
  title     = {Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation},
  journal   = {CoRR},
  volume    = {abs/1609.08144},
  year      = {2016},
  url       = {http://arxiv.org/abs/1609.08144},
}

@INPROCEEDINGS{Ma06champollion:a,
    author = {Xiaoyi Ma},
    title = {Champollion: A Robust Parallel Text Sentence Aligner},
    booktitle = {Proceedings of LREC-2006},
    year = {2006}
}

@article{journals/corr/abs-1301-3781,
  author = {Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
  journal = {CoRR},
  title = {Efficient Estimation of Word Representations in Vector Space},
  volume = {abs/1301.3781},
  year = 2013
}

@inproceedings{Heafield-estimate,
  author = {Kenneth Heafield and Ivan Pouzyrevsky and Jonathan H. Clark and Philipp Koehn},
  title = {Scalable Modified {Kneser-Ney} Language Model Estimation},
  year = {2013},
  booktitle = {Proceedings of the 51st Annual Meeting of the ACL},
  pages = {690--696},
}

@inproceedings{conf/acl/DurraniFSHK13,
  author = {Durrani, Nadir and Fraser, Alexander and Schmid, Helmut and Hoang, Hieu and Koehn, Philipp},
  booktitle = {ACL},
  isbn = {978-1-937284-51-0},
  keywords = {dblp},
  pages = {399-405},
  publisher = {The Association for Computer Linguistics},
  title = {Can {Markov} Models Over Minimal Translation Units Help Phrase-Based {SMT}?},
  year = 2013
}


@inproceedings{Gao:2008:PIW:1622110.1622119,
 author = {Gao, Qin and Vogel, Stephan},
 title = {Parallel Implementations of Word Alignment Tool},
 booktitle = {Software Engineering, Testing, and Quality Assurance for Natural Language Processing},
 year = {2008},
 isbn = {978-1-932432-10-7},
 location = {Columbus, Ohio},
 pages = {49--57},
 numpages = {9},
 url = {http://dl.acm.org/citation.cfm?id=1622110.1622119},
 acmid = {1622119},
 publisher = {ACL},
} 


@inproceedings{Koehn:2007:MOS:1557769.1557821,
 author = {Koehn, Philipp and Hoang, Hieu and Birch, Alexandra and Callison-Burch, Chris and Federico, Marcello and Bertoldi, Nicola and Cowan, Brooke and Shen, Wade and Moran, Christine and Zens, Richard and Dyer, Chris and Bojar, Ond\v{r}ej and Constantin, Alexandra and Herbst, Evan},
 title = {Moses: Open Source Toolkit for Statistical Machine Translation},
 booktitle = {Proceedings of the 45th Annual Meeting of the ACL},
 year = {2007},
 location = {Prague, Czech Republic},
 pages = {177--180},
 publisher = {ACL}
}

@inproceedings{DBLP:conf/emnlp/JohnsonMFK07,
  author    = {Howard Johnson and
               Joel D. Martin and
               George F. Foster and
               Roland Kuhn},
  title     = {Improving Translation Quality by Discarding Most of the Phrasetable},
  booktitle = {EMNLP-CoNLL 2007, Proceedings of the 2007 Joint Conference on Empirical
               Methods in Natural Language Processing and Computational Natural Language
               Learning, June 28-30, 2007, Prague, Czech Republic},
  pages     = {967--975},
  year      = {2007},
  timestamp = {Thu, 22 Jan 2015 16:51:46 +0100},
}

@article{junczys_mtm_2012,
  author = {Marcin Junczys-Dowmunt},
  title = {{Phrasal Rank-Encoding}: Exploiting Phrase Redundancy and Translational Relations for Phrase Table Compression},
  journal = {Prague Bull. Math. Linguistics},
  volume = {98},
  year = {2012},
  pages = {63--74},
  url = {http://ufal.mff.cuni.cz/pbml/98/art-junczys-dowmunt.pdf},
  abstract = {We describe Phrasal Rank-Encoding (PR-Enc), a novel method for the
  compression of word-aligned target language data in phrase tables as used in
  phrase-based SMT. This method reduces the redundancy in phrase tables which is
  a direct effect of the phrase-based approach. A combination of PR-Enc with
  Huffman coding allows to reduce the size of an aggressively compressed phrase
  table by another 39 percent. Using this and other methods for space reduction
  in a new binary phrase table implementation, a size reduction by an order of
  magnitude is achieved when comparing to the Moses on-disk phrase table
  implementation. Concerning decoding speed, all variants of the new phrase
  table are faster than the Moses binary phrase table implementation while the
  PR-Enc encoded variant outperforms all other methods.}
}

@article{junczys_psi-toolkit_2012,
  author = {Grali\'{n}ski, Filip and Jassem, Krzysztof and Junczys-Dowmunt, Marcin},
  journal = {Computational Linguistics - Applications},
  pages = {27--39},
  series = {Studies in Computational Intelligence},
  publisher = {Springer},
  title = {{PSI-Toolkit: Natural Language Processing Pipeline}},
  year = 2012,
  url = {http://emjotde.github.io/publications/pdf/mjd2012psitoolkit.pdf},
  abstract = {The paper presents the main ideas and the architecture of the open
  source PSI-Toolkit, a set of linguistic tools being developed within a project
  financed by the Polish Ministry of Science and Higher Education. The toolkit
  is intended for experienced language engineers as well as casual users not
  having any technological background. The former group of users is delivered a
  set of libraries that may be included in their Perl, Python or Java
  applications. The needs of the latter group should be satisfied by a user
  friendly web interface. The main feature of the toolkit is its data structure,
  the so-called PSI-lattice that assembles annotations delivered by all PSI
  tools. This cohesive architecture allows the user to invoke a series of
  processes with one command. The command has the form of a pipeline of
  instructions resembling shell command pipelines known from Linux-based
  system.}
}

@INPROCEEDINGS{Johnson07improvingtranslation,
    author = {J Howard Johnson and Joel Martin and George Forst and Roland Kuhn},
    title = {Improving translation quality by discarding most of the phrasetable},
    booktitle = {Proceedings of EMNLP-CoNLL'07},
    year = {2007},
    pages = {967--975}
}

@article{sennrich2011iterative,
  title={{Iterative, MT-based sentence alignment of parallel texts}},
  author={Sennrich, Rico and Volk, Martin},
  journal={18th Nordic Conference of Computational Linguistics, NODALIDA},
  year={2011}
}

@INPROCEEDINGS{Steinberger06thejrc-acquis:,
    author = {Ralf Steinberger and Bruno Pouliquen and Anna Widiger and Camelia Ignat and Toma\v{z} Erjavec and Dan Tufi\c{s}},
    title = {The {JRC-Acquis}: A multilingual aligned parallel corpus with 20+ languages},
    booktitle = {Proceedings of the 5th International Conference on Language Resources and Evaluation},
    year = {2006},
    pages = {2142--2147}
}

@InProceedings{CHEN12.641,
  author = {Yu Chen and Andreas Eisele},
  title = {{MultiUN} v2: {UN} Documents with Multilingual Alignments},
  booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)},
  year = {2012},
  month = {May},
  date = {23-25},
  address = {Istanbul, Turkey},
  editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet U?ur Do?an and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {978-2-9517408-7-7},
  language = {english}
 } 
 
 @inproceedings{citeulike:11979862,
    author = {Eisele, Andreas and Chen, Yu},
    booktitle = {Language Resources and Evaluation},
    citeulike-article-id = {11979862},
    keywords = {machine\_translation},
    posted-at = {2013-02-05 10:41:48},
    priority = {0},
    title = {{MultiUN}: A Multilingual Corpus from {United Nation} Documents},
    year = {2010}
}

@inproceedings{citeulike:5661570,
    abstract = {In this paper we describe a six-ways parallel public-domain corpus consisting of 2100 
    United Nations General Assembly Resolutions with translations in the six official languages of the United Nations, with an average of around 3 million tokens per language. The corpus is available in a pre-processed, formatting-normalized {TMX} format with paragraphs aligned across multiple languages. We describe the background to the corpus and its content, the process of its construction, and some of its interesting properties.},
    author = {Rafalovitch, Alexandre and Dale, Robert},
    booktitle = {MT Summit XII},
    citeulike-article-id = {5661570},
    citeulike-linkout-0 = {http://www.uncorpora.org/Rafalovitch\_Dale\_MT\_Summit\_2009.pdf},
    keywords = {corpus, united\_nations},
    location = {Ottawa, Canada},
    organization = {International Association of Machine Translation},
    pages = {292--299},
    posted-at = {2009-08-28 03:46:49},
    priority = {0},
    title = {{United Nations} General Assembly Resolutions: A Six-Language Parallel Corpus},
    url = {http://www.uncorpora.org/Rafalovitch\_Dale\_MT\_Summit\_2009.pdf},
    year = {2009}
}

@InProceedings{W15-4927,
   title={{SMT at the International Maritime Organization: experiences with combining in-house corpora with out-of-domain corpora}},
   author={Bruno Pouliquen and Marcin Junczys-Dowmunt and Blanca Pinero and Michal Ziemski},
   booktitle={Proceedings of the 18th Annual Conference of the European Association for Machine Translation},
   year={2015},
   address={Antalya, Turkey},
   url={http://aclweb.org/anthology/W15-4927},
   pages={202--205}
}

@inproceedings{44929,
title = {Addressing the Rare Word Problem in Neural Machine Translation},
author  = {Thang Luong and Ilya Sutskever and Quoc V. Le and Oriol Vinyals and Wojciech Zaremba},
year  = 2015,
URL = {http://arxiv.org/pdf/1410.8206v4.pdf},
booktitle = {ACL}
}


@inproceedings{pouliquen_coppa_2011,
author = {Bruno Pouliquen and Christophe Mazenc},
title = {{COPPA, CLIR and TAPTA: three tools to assist in overcoming the patent barrier at WIPO}},
booktitle={Proc of MT-Summit XIII},
year = {2011},
address={ Xiamen, China},
pages = {24--30}
}

@inproceedings{pouliquen_tapta_2011,
author = {Bruno Pouliquen and Christophe Mazenc and Aldo Iorio},
title = {{TAPTA: A user-driven translation system for patent documents based on domain-aware statistical machine translation.}},
booktitle={Proceedings of the 15th Annual Conference of the EAMT},
year = {2011},
address={Trento, Italy},
pages = {5-12}
}

@inproceedings{junczys_mtsummit_2013,
  author = {Bruno Pouliquen and Cecilia Elizalde and Marcin Junczys-Dowmunt and Christophe Mazenc and Jos\'{e} Garc\'{i}a-Verdugo},
  title = {{Large-scale multiple language translation accelerator at the United Nations}},
  booktitle = {MT-Summit XIV},
  year = {2013},
  pages = {345--352},
}