thesis.bib

@InProceedings{	  baronisilvia2004,
  author	= {Marco Baroni and Silvia Bernardini},
  title		= {{BootCaT}: Bootstrapping corpora and terms from the web},
  year		= {2004},
  pages		= {1313--1316},
  crossref	= {lrec2004},
  file		= {bootcat_lrec_2004.pdf:http\://sslmit.unibo.it/~baroni/lrec2004/bootcat_lrec_2004.pdf:PDF}
		  ,
  owner		= {egon},
  timestamp	= {2008.08.17},
  url		= {http://sslmit.unibo.it/~baroni/publications/lrec2004/bootcat_lrec_2004.pdf}
		  
}

@InProceedings{	  baronichantreekilgarriffsharoff2008,
  author	= {Marco Baroni and Francis Chantree and Kilgarriff and Serge
		  Sharoff},
  title		= {{C}lean{E}val: A competition for cleaning Web pages},
  year		= {2008},
  crossref	= {lrec2008},
  file		= {lrec08-cleaneval.pdf:http\://clic.cimec.unitn.it/marco/publications/lrec2008/lrec08-cleaneval.pdf:PDF}
		  ,
  owner		= {egon},
  timestamp	= {2008.08.15},
  url		= {http://clic.cimec.unitn.it/marco/publications/lrec2008/lrec08-cleaneval.pdf}
		  
}

@InProceedings{	  fiasco2007,
  author	= {Daniel Bauer and Judith Degen and Xiaoye Deng and Priska
		  Herger and Jan Gasthaus and Eugenie Giesbrecht and Lina
		  Jansen and Christin Kalina and Thorben Kr\"{u}ger and
		  Robert M\"{a}rtin and Martin Schmidt and Simon Scholler and
		  Johannes Steger and Egon Stemle and Stefan Evert},
  title		= {{FIASCO}: {F}iltering the {I}nternet by {A}utomatic
		  {S}ubtree {C}lassification, {O}snabr\"{u}ck},
  year		= {2007},
  crossref	= {WAC3},
  owner		= {egon},
  timestamp	= {2007.11.20},
  url		= {http://purl.org/stefan.evert/PUB/BauerEtc2007_FIASCO.pdf}
}

@InProceedings{	  evert2008,
  author	= {Stefan Evert},
  title		= {A lightweight and efficient tool for cleaning Web pages},
  year		= {2008},
  abstract	= {Originally conceived as a 'naive' baseline experiment
		  using traditional n-gram language models as classifiers,
		  the NCLEANER system has turned out to be a fast and
		  lightweight tool for cleaning Web pages with
		  state-of-the-art accuracy (based on results from the
		  CLEANEVAL competition held in 2007). Despite its
		  simplicity, the algorithm achieves a significant
		  improvement over the baseline (i.e. plain, uncleaned text
		  dumps), trading off recall for substantially higher
		  precision. NCLEANER is available as an open-source software
		  package. It is preconfigured for English Web pages, but can
		  adapted to other languages with minimal amounts of manually
		  cleaned training data. Since NCLEANER does not make use of
		  HTML structure, it can also be applied to existing Web
		  corpora that are only available in plain text format, with
		  a minor loss in classification accuracy.},
  crossref	= {lrec2008},
  file		= {Evert2008_NCleaner.pdf:http\://purl.org/stefan.evert/PUB/Evert2008_NCleaner.pdf:PDF}
		  ,
  owner		= {egon},
  timestamp	= {2008.08.15},
  url		= {http://purl.org/stefan.evert/PUB/Evert2008_NCleaner.pdf}
}

@InProceedings{	  spoustamarekpecina2008,
  author	= {Miroslav Spousta and Michal Marek and Pavel Pecina},
  title		= {Victor: the Web-Page Cleaning Tool},
  booktitle	= {Proceedings of the 4th Web as Corpus Workshop ({WAC}4) --
		  Can we beat {G}oogle?},
  year		= {2008},
  crossref	= {WAC4},
  owner		= {egon},
  timestamp	= {2009.04.02}
}

@WEBPAGE{	  debian.org,
  title		= {Debian {GNU}/{L}inux: The free Operating System for your
		  Computer},
  url		= {http://www.debian.org/},
  lastchecked	= {032009},
  key		= {{@DEB}},
  crossref	= {gnu.org},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@WEBPAGE{	  firefox,
  title		= {Firefox: The Browser That Has It All},
  url		= {http://www.mozilla.com/firefox/},
  lastchecked	= {032009},
  key		= {{@FF}},
  crossref	= {mozilla.org},
  owner		= {egon},
  timestamp	= {2008.08.17}
}

@Article{	  artsteinpoesio2008,
  author	= {Artstein, Ron and Poesio, Massimo},
  title		= {Inter-Coder Agreement for Computational Linguistics},
  journal	= {Computational Linguistics},
  year		= {2008},
  volume	= {34},
  pages		= {555-596},
  number	= {4},
  abstract	= {This article is a survey of methods for measuring
		  agreement among corpus annotators. It exposes the
		  mathematics and underlying assumptions of agreement
		  coefficients, covering Krippendorff's alpha as well as
		  Scott's pi and Cohen's kappa; discusses the use of
		  coefficients in several annotation tasks; and argues that
		  weighted, alpha-like coefficients, traditionally less used
		  than kappa-like measures in computational linguistics, may
		  be more appropriate for many corpus annotation tasks -- but
		  that their use makes the interpretation of the value of the
		  coefficient even harder.},
  doi		= {10.1162/coli.07-034-R2},
  eprint	= {http://www.mitpressjournals.org/doi/pdf/10.1162/coli.07-034-R2}
		  ,
  owner		= {egon},
  timestamp	= {2009.04.05},
  url		= {http://www.mitpressjournals.org/doi/abs/10.1162/coli.07-034-R2}
		  
}

@WEBPAGE{	  cleaneval/annotation_guidelines,
  title		= {{CLEANEVAL}: Guidelines for annotators},
  url		= {http://cleaneval.sigwac.org.uk/annotation_guidelines.html}
		  ,
  author	= {Marco Baroni and Serge Sharoff},
  lastchecked	= {032009},
  key		= {{@CEannos}},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@WEBPAGE{	  wwwoffle,
  title		= {A simple proxy server with special features for use with
		  dial-up Internet Links},
  url		= {http://gedanken.demon.co.uk/wwwoffle/},
  author	= {Andrew M. Bishop},
  lastchecked	= {032009},
  key		= {{@WOFFL}},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@InProceedings{	  grefenstettenioche2000,
  author	= {Gregory Grefenstette and Julien Nioche},
  title		= {Estimation of English and non-English language use on the
		  {WWW}},
  booktitle	= {In Recherche d'Information Assist\'{e}e par Ordinateur
		  ({RIAO})},
  year		= {2000},
  pages		= {237--246},
  owner		= {egon},
  timestamp	= {2009.03.27}
}

@WEBPAGE{	  url,
  title		= {Uniform Resource Locators: A Syntax for the Expression of
		  Access Information of Objects on the Network},
  url		= {http://www.w3.org/Addressing/URL/url-spec.txt},
  author	= {{URI} working Group},
  lastchecked	= {032009},
  key		= {{@URL}},
  comment	= {cf. w3.org/Addressing},
  organization	= {W3C},
  owner		= {egon},
  timestamp	= {2009.03.19}
}

@Article{	  kilgarriff2007,
  author	= {Kilgarriff,, Adam},
  title		= {Googleology is Bad Science},
  journal	= {Comput. Linguist.},
  year		= {2007},
  volume	= {33},
  pages		= {147--151},
  number	= {1},
  address	= {Cambridge, MA, USA},
  doi		= {http://dx.doi.org/10.1162/coli.2007.33.1.147},
  issn		= {0891-2017},
  owner		= {egon},
  publisher	= {MIT Press},
  timestamp	= {2009.03.27}
}

@Article{	  kilgarriffgrefenstette03,
  author	= {Adam Kilgarriff and Gregory Grefenstette},
  title		= {Introduction to the special issue on the web as corpus},
  journal	= {Computational Linguistics},
  year		= {2003},
  volume	= {29},
  pages		= {333--347},
  owner		= {egon},
  timestamp	= {2009.03.21}
}

@Manual{	  r-project,
  title		= {R: A Language and Environment for Statistical Computing},
  author	= {{R Development Core Team}},
  organization	= {R Foundation for Statistical Computing},
  address	= {Vienna, Austria},
  year		= {2008},
  note		= {{ISBN} 3-900051-07-0},
  owner		= {egon},
  timestamp	= {2009.04.05},
  url		= {http://www.R-project.org}
}

@Article{	  vips,
  author	= {Song Ruihua and Liu Haifeng and Wen Ji-Rong and Ma
		  Wei-Ying},
  title		= {Learning important models for web page blocks based on
		  layout and content analysis},
  journal	= {SIGKDD Explor. Newsl.},
  year		= {2004},
  volume	= {6},
  pages		= {14--23},
  number	= {2},
  address	= {New York, NY, USA},
  doi		= {http://doi.acm.org/10.1145/1046456.1046459},
  issn		= {1931-0145},
  owner		= {egon},
  publisher	= {ACM},
  timestamp	= {2009.04.06}
}

@WEBPAGE{	  krdwrd.org,
  title		= {The {K}rd{W}rd Project Web Site},
  url		= {https://krdwrd.org/},
  author	= {Johannes M. Steger and Egon W. Stemle},
  lastchecked	= {032009},
  key		= {{@KRDWRD}},
  owner		= {egon},
  timestamp	= {2008.08.15}
}

@WEBPAGE{	  w3.org/addressing,
  title		= {Naming and Addressing: {URIs}, {URLs}, \ldots},
  url		= {http://www.w3.org/Addressing/},
  author	= {W3C},
  lastchecked	= {032009},
  key		= {{@ADDRESSING}},
  organization	= {W3C},
  owner		= {egon},
  timestamp	= {2009.03.19}
}

@Proceedings{	  lrec2004,
  title		= {Proceedings of the 4th International Conference on
		  Language Resources and Evaluation ({LREC} 2004)},
  year		= {2004},
  editor	= {European Language Resources Association (ELRA)},
  address	= {Lisbon, Portugal},
  month		= may,
  owner		= {egon},
  timestamp	= {2008.08.17},
  url		= {http://www.lrec-conf.org/lrec2004/}
}

@Proceedings{	  lrec2008,
  title		= {Proceedings of the 6th International Conference on
		  Language Resources and Evaluation ({LREC} 2008)},
  year		= {2008},
  editor	= {European Language Resources Association ({ELRA})},
  address	= {Marrakech, Morocco},
  month		= may,
  owner		= {egon},
  timestamp	= {2008.08.17},
  url		= {http://www.lrec-conf.org/lrec2008/}
}

@Proceedings{	  corpuslinguistics2005,
  title		= {Proceedings of Corpus Linguistics 2005},
  year		= {2005},
  editor	= {Pernilla Danielsson and Martijn Wagenmakers},
  volume	= {1},
  series	= {The Corpus Linguistics Conference Series},
  note		= {ISSN 1747-9398},
  owner		= {egon},
  timestamp	= {2009.03.27}
}

@Proceedings{	  wac4,
  title		= {Can we beat Google? ({WAC}4 - 2008) -- Proceedings of the
		  4th web as corpus workshop},
  year		= {2008},
  editor	= {Stefan Evert and Adam Kilgarriff and Serge Sharoff},
  month		= {06},
  owner		= {egon},
  timestamp	= {2009.03.23},
  url		= {http://webascorpus.sourceforge.net/download/WAC4_2008_Proceedings.pdf}
		  
}

@Proceedings{	  wac3,
  title		= {Building and Exploring Web Corpora ({WAC}3 - 2007) --
		  Proceedings of the 3rd web as corpus workshop,
		  incorporating {CLEANEVAL}},
  year		= {2007},
  editor	= {C\'{e}drick Fairon and Hubert Naets and Adam Kilgarriff
		  and Gilles-Maurice de Schryver},
  address	= {Louvain-la-Neuve},
  publisher	= {Presses universitaires de Louvain},
  month		= jul,
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@Proceedings{	  wac2,
  title		= {11th Conference of the European Chapter of the Association
		  for Computational Linguistics -- Proceedings of the 2nd
		  International Workshop on Web as Corpus},
  year		= {2006},
  editor	= {Adam Kilgarriff and Marco Baroni},
  address	= {Trento, Italy},
  month		= apr,
  owner		= {egon},
  timestamp	= {2009.03.21},
  url		= {http://www.aclweb.org/anthology-new/W/W06/W06-1700.pdf}
}

@Booklet{	  bnc/userlicence,
  title		= {The {B}ritish {N}ational {C}orpus ({BNC}) User Licence},
  howpublished	= {Online Version},
  lastchecked	= {032009},
  organization	= {University of Oxford},
  owner		= {egon},
  timestamp	= {2009.03.27},
  url		= {http://www.natcorp.ox.ac.uk/docs/licence.pdf}
}

@WEBPAGE{	  cgi,
  title		= {The {C}ommon {G}ateway {I}nterface ({CGI}) -- a standard
		  for external gateway programs to interface with information
		  servers such as HTTP servers},
  url		= {http://hoohoo.ncsa.uiuc.edu/cgi/overview.html},
  lastchecked	= {032009},
  key		= {{@CGI}},
  owner		= {egon},
  timestamp	= {2009.03.21}
}

@WEBPAGE{	  gnu.org,
  title		= {{GNU} operating system},
  url		= {http://www.gnu.org/},
  lastchecked	= {032009},
  key		= {{@GNU}},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@WEBPAGE{	  httpd.apache.org,
  title		= {The Apache {HTTP} Server Project},
  url		= {http://httpd.apache.org/},
  lastchecked	= {032009},
  key		= {{@HTTP}},
  organization	= {The Apache Software Foundation},
  owner		= {egon},
  timestamp	= {2009.03.21}
}

@WEBPAGE{	  ikw/cl,
  title		= {The Computational Linguistics Group of the {I}nstitute of
		  {C}ognitive {S}cience at the {U}niversity of
		  {O}snabr\"{u}ck},
  url		= {http://www.ikw.uni-osnabrueck.de/CL/},
  lastchecked	= {032009},
  key		= {{@CL}},
  owner		= {egon},
  timestamp	= {2009.03.22}
}

@Manual{	  krdwrd.org/manual,
  title		= {Add-on Manual},
  organization	= {The KrdWrd Project},
  note		= {Online Version at \url{https://krdwrd.org/manual/html/}},
  owner		= {egon},
  timestamp	= {2009.04.04},
  url		= {https://krdwrd.org/manual/manual.pdf}
}

@WEBPAGE{	  mozilla.org,
  title		= {The Mozilla project},
  url		= {http://www.mozilla.org/},
  lastchecked	= {032009},
  key		= {{@MOZILLA}},
  organization	= {Mozilla Corporation},
  owner		= {egon},
  timestamp	= {2008.08.17}
}

@WEBPAGE{	  potamodule,
  title		= {A Perl module intended to perform ``boilerplate''
		  stripping and other forms of filtering},
  url		= {http://sslmitdev-online.sslmit.unibo.it/wac/post_processing.php}
		  ,
  lastchecked	= {032009},
  key		= {{@POTA}},
  organization	= {SSLMIT Dev, University of Bologna},
  owner		= {egon},
  timestamp	= {2009.03.23}
}

@WEBPAGE{	  python,
  title		= {Python: An interpreted, interactive, object-oriented
		  programming language},
  url		= {http://www.python.org/},
  lastchecked	= {032009},
  key		= {{@PYTHON}},
  owner		= {egon}
}

@WEBPAGE{	  subversion,
  title		= {An open source version control system},
  url		= {http://subversion.tigris.org/},
  lastchecked	= {032009},
  key		= {{@SVN}},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@WEBPAGE{	  sz-archiv.de/agb,
  title		= {S\"{u}ddeutsche {Z}eitung {A}rchiv -- {A}llgemeine
		  {G}esch\"{a}ftsbedingungen},
  url		= {http://www.sz-archiv.de/sueddeutsche-zeitung-archiv/onlinearchive/sz-aboarchiv-ubersicht/sz-aboarchiv-agb}
		  ,
  lastchecked	= {032009},
  key		= {{@SZAGB}},
  organization	= {DIZ München GmbH},
  owner		= {egon},
  timestamp	= {2009.03.27}
}

@WEBPAGE{	  trac,
  title		= {An enhanced Wiki and issue tracking system for software
		  development projects},
  url		= {http://trac.edgewall.org/},
  lastchecked	= {032009},
  key		= {{@TRAC}},
  owner		= {egon},
  timestamp	= {2008.08.16}
}

@WEBPAGE{	  unicode.org,
  title		= {Unicode Home Page},
  url		= {http://www.unicode.org/},
  lastchecked	= {032009},
  key		= {{@UNICODE}},
  organization	= {Unicode, Inc.},
  owner		= {egon}
}

@WEBPAGE{	  w3.org/base,
  title		= {{HTML} 4.01 Specification -- Path information: the {BASE}
		  element},
  url		= {http://www.w3.org/TR/html401/struct/links.html#h-12.4},
  lastchecked	= {032009},
  key		= {{@W3base}},
  organization	= {The {W}orld {W}ide {W}eb Consortium ({W3C})},
  owner		= {egon},
  timestamp	= {2008.08.17}
}

@WEBPAGE{	  wc,
  title		= {The wc Command},
  url		= {http://www.bellevuelinux.org/wc.html},
  lastchecked	= {032009},
  key		= {{@WC}},
  owner		= {egon},
  timestamp	= {2009.03.23}
}

@WEBPAGE{	  yahoo,
  title		= {The {Yahoo!}~Internet search engine},
  url		= {http://www.yahoo.com},
  lastchecked	= {032009},
  key		= {{@YAHOO}},
  organization	= {Yahoo!},
  owner		= {egon},
  timestamp	= {2009.03.22}
}
@inproceedings{Steger08,
  author = {Johannes Steger and Niklas Wilming and Felix Wolfsteller and Nicolas H\"oning and Peter K\"onig},
  booktitle = {WAPCV},
  editor = {Lucas Paletta and John K. Tsotsos},
  interHash = {704e542c1aaef3839a566c64998ac686},
  intraHash = {c0494621b8f35d0f701a7c8bcb6847fa},
  pages = {153-165},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {The JAMF Attention Modelling Framework.},
  url = {http://dblp.uni-trier.de/db/conf/wapcv/wapcv2008.html#StegerWWHK08},
  volume = {5395},
  year = {2008},
  ee = {http://dx.doi.org/10.1007/978-3-642-00582-4_12},
  isbn = {978-3-642-00581-7},
  date = {2009-02-24}
}

@Manual{libsvm,
  author ={Chih-Chung Chang and Chih-Jen Lin},
  title = {{LIBSVM}: a library for support vector machines},
  year = {2001},
  note = {Software available at \url{http://www.csie.ntu.edu.tw/~cjlin/libsvm}}
}

@techreport{dom,
  title = {Document Object Model (DOM) Level 3 Core Specification},
  year = {2004},
  author = {Arnaud Le Hors and Philippe Le H\'{e}garet and Lauren Wood and Gavin Nicol and Jonathan Robie and Mike Champion and Steve Byrne},
  institution = {W3C},
  type = {Recommendation}
}
@techreport{xul,
  title = {XML User Interface Language (XUL) 1.0},
  year = {2001},
  author = {Ben Goodger and Ian Hickson and David Hyatt and Chris Waterson},
  editor = {David Hyatt},
  institution = {Mozilla.org},
  type = {Recommendation}
}
@inproceedings{bootcat,
author={M. Baroni and S. Bernardini},
year={2004},
title={BootCaT: Bootstrapping corpora and terms from the web},
series = {Proceedings of LREC 2004}
}
@comment{
@TECHREPORT{NajorkHeydon2001,
  author = {Marc Najork and Allan Heydon},
  title = {High-performance web crawling},
  institution = {SRC Research Report 173, Compaq Systems Research},
  year = {2001},
  citeseerurl = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.7568},
  url = {ftp://gatekeeper.research.compaq.com/pub/DEC/SRC/research-reports/SRC-173.ps.gz}
}

@INPROCEEDINGS{ShkapenyukSuel2002,
  author = {Vladislav Shkapenyuk and Torsten Suel},
  title = {Design and implementation of a high-performance distributed web crawler},
  booktitle = {In Proc. of the Int. Conf. on Data Engineering},
  year = {2002},
  pages = {357--368},
  citeseerurl = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.4762},
  url = {http://cis.poly.edu/~suel/papers/crawl.ps}
}
}

@inproceedings{StegerStemle2009,
    abstract = {Algorithmic processing of Web content mostly works on textual contents, neglecting visual information. Annotation tools largely share this deficit as well. We specify requirements for an architecture to overcome both problems and propose an implementation, the KrdWrd system. It uses the Gecko rendering engine for both annotation and feature extraction, providing unified data access in every processing step. Stable data storage and collaboration control scripts for group annotations of massive corpora are provided via a Web interface coupled with a HTTP proxy. A modular interface allows for linguistic and visual data feature extractor plugins. The implementation is suitable for many tasks in theWeb as corpus domain and beyond.},
    address = {Donostia-San Sebastian, Basque Country},
    author = {Steger, Johannes M. and Stemle, Egon W.},
    booktitle = {Proceedings of the Fifth Web as Corpus Workshop (WAC5)},
    file = {:home/egon/Books/mndlyBooks/Steger, Stemle/Proceedings of the Fifth Web as Corpus Workshop (WAC5)/Steger, Stemle - 2009 - {KrdWrd} Architecture for Unified Processing of Web Content.pdf:pdf},
    title = {{{KrdWrd} Architecture for Unified Processing of Web Content}},
    year = {2009}
}