%%%%%%%%%%Bibliography related to the MULTEXT-East project
%%2003-10-27
%%Toma\v{z} Erjavec


%%%%%%%%%%%%%%%%%Overview papers:

@inproceedings{mte:slav,
  author = "Toma\v{z} Erjavec and Cvetana Krstev and 
            Vladim\'{\i}r Petkevi\v{c} and Kiril Simov and 
            Marko Tadi\'{c} and Du\v{s}ko Vitas",
  title  = "{The MULTEXT-East Morphosyntactic Specifications for 
             Slavic Languages}",
  booktitle = "Proceedings of the EACL 2003 Workshop on Morphological
               Processing of Slavic Languages",
  pages = {25-32},
  address = "Budapest",
  year = "2003",
  note = {http://nl.ijs.si/ME/V2/}
}

@inproceedings{mte:nlprs,
  author = "Toma\v{z} Erjavec",
  title  = "{Harmonised Morphosyntactic Tagging for Seven Languages 
             and Orwell's 1984}",
  booktitle = "6th Natural Language Processing Pacific Rim 
               Symposium, NLPRS'01 ",
  pages = {487-492},
  address = "Tokyo",
  year = "2001",
  note = {http://nl.ijs.si/ME/V2/}
}

@Article{elsnews01:v2,
  author =	 {Toma\v{z} Erjavec},
  title =	 "{The MULTEXT-East Resources Revisited}",
  journal =	 {ElsNews},
  year =	 2001,
  volume =	 10,
  number =	 1,
  pages =        "3--2"
}

@InProceedings{coling98:mte,
  author =       "Ludmila Dimitrova and Toma\v{z} Erjavec and Nancy
                  Ide and Heiki-Jan Kaalep 
                  and Vladim\'{\i}r Petkevi\v{c} and 
                  Dan Tufi\c{s}",
  title =        "{Multext-East: Parallel and Comparable Corpora 
                  and Lexicons for Six Central and Eastern
                  European Languages}",
  booktitle =    "COLING-ACL '98",
  pages =        "315-319",
  address =      "Montr\'eal, Qu\'ebec, Canada",
  year =         1998
}

@InProceedings{lrec98:mtecorp,
  author =       "Toma\v{z} Erjavec and Nancy Ide",
  title =        "The {MULTEXT-East} Corpus",
  pages =        "971--974",
  booktitle =    "First International Conference on Language Resources
                  and Evaluation, LREC'98",
  address =      "Granada",
  year =         1998,
  organization = "ELRA"
}

@InProceedings{lrec98:mtelex,
  author =       "Nancy Ide and Dan Tufi\c{s} and Toma\v{z} Erjavec",
  title =        "{Development and Assessment of Common Lexical Specifications
                  for Six Central and Eastern European Languages}",
  pages =        "233--240",
  booktitle =    "First International Conference on Language Resources
                  and Evaluation, LREC'98",
  address =      "Granada",
  year =         1998,
  organization = "ELRA"
}

@Misc{telri:CD,
  author =       "Toma\v{z} Erjavec and Ann Lawson and Laurent Romary",
  title =        "{East meets West: A Compendium of Multilingual Resources}",
  howpublished = "CD-ROM",
  year =         1998,
  organization = "TELRI Association e.V",
  note =         "ISBN: 3-922641-46-6",
}

@InProceedings{lrec98:mtecd,
  author =       "Toma\v{z} Erjavec and Ann Lawson and Laurent Romary",
  title =        "{East meets West: 
                  Producing Multilingual Resources in a European Context}",
  pages =        "233--240",
  booktitle =    "First International Conference on Language Resources
                  and Evaluation, LREC'98",
  address =      "Granada",
  year =         1998,
  organization = "ELRA",
  note =         "http://nl.ijs.si/ME/"
}

@InProceedings{lrec98:ces,
  author =       "Nancy Ide",
  title =        "{Corpus Encoding Standard}: {SGML} Guidelines for
                  Encoding Linguistic Corpora",
  pages =        "463--470",
  booktitle =    "First International Conference on Language Resources
                  and Evaluation, LREC'98",
  address =      "Granada",
  year =         1998,
  organization = "ELRA",
  note = "http://www.cs.vassar.edu/CES/"
}

@InProceedings{Erj:TihMTE,
  author = 	 "Toma\v{z} Erjavec and Nancy Ide and 
                   Vladim\'{\i}r Petkevi\v{c} and Jean V\'{e}ronis",
  title = 	 "{MULTEXT-East}: Multilingual Text Tools and Corpora 
                  for {Central and Eastern European} Languages",
  booktitle =	 "Proceedings of the First TELRI European Seminar:
                  Language Resources for Language Technology",
  year =	 "1996",
  pages =        "87--98",
  note =	 "15--16 September 1995, Tihany, Hungary"
}

@InProceedings{coling94:mt,
  author =       "Nancy Ide and Jean V\'{e}ronis",
  title =        "MULTEXT (Multilingual Tools and Corpora)",
  booktitle =    "Proceedings of the 15th CoLing",
  address =      "Kyoto",
  year =         "1994",
  pages =        "90-96"
}

%%%%%%%%%%%%%%%%%%Deliverable reports on MULTEXT-East and related projects:

@TechReport{MTE:D11F,
  key  =         "Toma\v{z} Erjavec and Monica Monachini",
  title =        "Specifications and Notation for Lexicon Encoding",
  type =         "{MULTEXT-East} Final Report",
  number =       "D1.1F",
  year =         "1997",
  month =        "December",
  editor =       "Toma\v{z} Erjavec and Monica Monachini",
  institution =  "Institute Jo\v{z}ef Stefan",
  address =      "Ljubljana, Slovenia",
  note =         "http://nl.ijs.si/ME/CD/docs/mte-d11f/"
}

@TechReport{MTE:D21F,
  title =        "Sample Corpus Collection and Preparation",
  type =         "MULTEXT-East Final Report",
  number =       "D2.1F",
  year =         "1997",
  month =        "December",
  editor =       "Toma\v{z} Erjavec (ed.)",
  author =       "Ludmila Dimitrova and Lydia Sinapova and 
                  Vladimir Petkevi\v{c} and 
                  Jana Kl\'{\i}mov\'{a} and Vera Schmiedtov\'{a} and
                  Heiki-Jan Kaalep and 
                  Viire Villandi and Heili Orav and 
                  Leho Paldre and Urve Talvik and Kadri Muischnek and
                  Csaba Oravecz and Laszlo Tihanyi and 
                  \c{S}tefan Bruda and C\u{a}lin Diaconu and 
                  Lidia Diaconu and Dan Tufi\c{s} and 
                  Toma\v{z} Erjavec and Miro Romih and Olga Vukovi\v{c}",
  institution =  "Institute Jo\v{z}ef Stefan",
  address =      "Ljubljana, Slovenia",
  note =         "70pp",
}
                 
@TechReport{MTE:D23F,
  title =        "Corpus Markup",
  type =         "MULTEXT-East Final Report",
  number =       "D2.3F",
  year =         "1997",
  month =        "December",
  author =       "Greg-Priest Dorman and Toma\v{z} Erjavec and Nancy
                  Ide and Vladimir Petkevi\v{c}",
  institution =  "Institute Jo\v{z}ef Stefan",
  address =      "Ljubljana, Slovenia",
  note =         "34pp"
                  }

@TechReport{mt:mtseg,
  title =        "MtSeg: The Multext multilingual segmenter tools",
  type =         "MULTEXT Deliverable",
  number =       "MSG 1, Version 1.3.1",
  year =         "1996",
  author =       "Philippe Di Cristo",
  institution =  "CNRS",
  address =      "Aix-en-Provence",
  note =         "http://www.lpl.univ-aix.fr/projects/multext/MtSeg/"
                  }

@TechReport{mt:D161B,
  title =        "Common Specifications and Notation for Lexicon
                  Encoding and Preliminary Proposal for the Tagsets",
  type =         "MULTEXT Deliverable",
  number =       "D1.6.1B",
  year =         "1995",
  editor =       "Nuria Bel, Nicoletta Calzolari and Monica Monachini",
  author =       "Nuria Bel and Nicoletta Calzolari and Monica Monachini (eds.)",
  institution =  "ILC",
  address =      "Pisa"
}

@TechReport{eagles:morphana,
  title =        "Recommendations for the Morphosyntactic Annotation of Corpora",
  author =       "Geoffrey Leech and Andrew Wilson",
  type =         "EAGLES Report",
  number =       "EAG--TCWG--MAC/R",
  year =         "1996",
  institution =  "ILC",
  address =      "Pisa",
  note = "http://www.ilc.cnr.it/EAGLES96/annotate/"
}

@TechReport{eagles:morphsyn,
  title = "Synopsis and Comparison of Morphosyntactic Phenomena
  Encoded in Lexicons and Corpora: A Common Proposal and Applications
  to European Languages",
  author =       "Nicoletta Calzolari and Monica Monachini (eds.)",
  type =         "EAGLES Report",
  number =       "EAG---CLWG---MORPHSYN/R",
  year =         "1996",
  institution =  "ILC",
  address =      "Pisa",
  note = "http://www.ilc.cnr.it/EAGLES96/morphsyn/"
}

@TechReport{eagles:morphsyn-de,
  title = "EAGLES specification for German morphosyntax",
  author =       "Simone Teufel and Christine St\u{o}ckert",
  year =         "1996"
}

%%%%%%%%%%Sense disambiguation:
                  
@Article{ide00:wsd,
  author =       "Nancy Ide",
  title =        "{Cross-lingual sense determination: Can it work?}",
  journal =      "Computers and the Humanities",
  pages =        "223-34",
  volume =       "34",
  number =       "1-2",
  year =         "2000"
}

@InProceedings{IdeErjTuf2001,
  author =       "Nancy Ide and Toma\v{z} Erjavec and Dan Tufi\c{s}",
  title =        "{Automatic Sense Tagging Using Parallel Corpora}",
  pages =        "83-89",
  booktitle =    "Proceedings of the Sixth Natural Language Processing Pacific Rim Symposium",
  year =         2001,
  address = "Tokyo",
}

@InProceedings{IdeErjTuf2002,
  author =       "Nancy Ide and Toma\v{z} Erjavec and Dan Tufi\c{s}",
  title =        "{Sense Discrimination with Parallel Corpora}",
  pages =        "54-60",
  booktitle =    "Workshop on Word Sense Disambiguation: Recent Successes and Future Directions",
  year =         2002,
  address = "Philadelphia",
  organization = "ACL",
  month =        "July"
}

%%%%%%%%%%%%%%%%Tagging experiments:

@InProceedings{anlp00:hajic,
  author =       "Jan Haji\v{c}",
  title =        "{Morphological Tagging: Data vs.\ Dictionaries}",
  booktitle =    "ANLP/NAACL 2000",
  address =      "Seatle",
  year =         2000
}

@InProceedings{lnia99:tufis,
  author =       "Dan Tufi\c{s}",
  title =        "{Tiered Tagging and Combined Language Model Classifiers}",
  editor =       "Jelinek and Noth",
  booktitle =    "Text, Speech and Dialogue",
  number =       1692,
  series =       "Lecture Notes in Artificial Intelligence",
  pages =        "28--33",
  year =         1999,
  publisher =    {Springer-Verlag}
}

@InProceedings{lrec00:tufis,
  author =       "Dan Tufi\c{s}",
  title =        "{Using a Large Set of EAGLES-compliant
                  Morpho-Syntactic Descriptors as Tags for
                  Probabilistic Tagging}",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"
}

@InProceedings{tufis:eq01,
  author =       "Dan Tufi\c{s} and Ana Maria Barbu",
  title =        "{Accurate Automatic extraction of Translation
		  Equivalents from Parallel Corpora}",
  booktitle =    "Proceedings of the Corpus Linguistics 2001 conference",
  address =      "Lancaster",
  pages =        "581-586",
  series = 	 "UCREL technical paper",
  volume = 13,
  year =         2001,
}

@techreport{dzerza99,
        author = "Sa\v{s}o D\v{z}eroski and Toma\v{z} Erjavec and 
                  Jakub Zavrel",
        title  = "Morphosyntactic Tagging of Slovene: 
                  Evaluating PoS Taggers and Tagsets",
        type = "Research Report",
        number = "IJS-DP 8018",
        institution = "Jo\v{z}ef Stefan Institute",
        address = "Ljubljana, Slovenia",
        year = "1999",
        note = "http://nl.ijs.si/lll/bib/dzerza-report/"
}

@InProceedings{lrec00:dzeroskietal,
  author =       "Sa\v{s}o D\v{z}eroski and Toma\v{z} Erjavec and
                  Jakub Zavrel",
  title =        "{Morphosyntactic Tagging of Slovene: Evaluating PoS
                   Taggers and Tagsets}",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"
}

@InProceedings{lrec00:tufisetal,
  author =       "Dan Tufi\c{s} and Peter Dienes and Csaba Oravecz and
                  Tamas Varadi",
  title =        "Principled Hidden Tagset Design for Tiered Tagging
                  of Hungarian",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"
}

@InProceedings{lrec00:bohus,
  author =       "Marian Boldea Bohus",
  title =        "A Web-Based Text Corpora Development System",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA",
  note = {http://www.cs.cmu.edu/People/dbohus/docs/wbtcds\_lrec2000.ps.gz}
}


%%%Papers on Machine Learning, esp. ILP:
%%%Bibliography from http://www.cs.york.ac.uk/mlg/lll/

@InProceedings{cussens99:_morph,
  author =       {James Cussens and Sa\v{s}o D\v{z}eroski and Toma\v{z} Erjavec},
  title =        {Morphosyntactic Tagging of {S}lovene using {P}rogol},
  booktitle =    {Inductive Logic Programming: Proc.\ of the 9th International Workshop (ILP-99)},
  year =         1999,
  editor =       {Sa\v{s}o D\v{z}eroski and Peter Flach},
  address =      {Bled, Slovenia},
  month =        {June},
  series =       "Lecture Notes in Artificial Intelligence",
  number =       1634,
  pages =        "68-79",
  publisher =    {Springer-Verlag},
  abstract = {We consider the task of tagging Slovene words with morphosyntactic
  descriptions (MSDs). MSDs contain not only part-of-speech
  information but also attributes such as gender and case. In the case
  of Slovene there are 2,083 possible MSDs. P-Progol was used to learn
  morphosyntactic disambiguation rules from annotated data (consisting
  of 161,314 examples) produced by the MULTEXT-East project.  P-Progol
  produced 1,148 rules taking 36 hours.  Using simple grammatical
  background knowledge, e.g.\ looking for case disagreement, P-Progol
  induced 4,094 clauses in eight parallel runs.  These rules have
  proved effective at detecting and explaining incorrect MSD
  annotations in an independent test set, but have not so far produced
  a tagger comparable to other existing taggers in terms of accuracy.}
}

@InProceedings{kazakov99:_learn,
  author =       {Dimitar Kazakov and Suresh Manandhar and Toma\v{z} Erjavec},
  title =        {Learning word segmentation rules for tag prediction},
  booktitle =    {Inductive Logic Programming: Proc.\ of the 9th International Workshop (ILP-99)},
  year =         1999,
  editor =       {Sa\v{s}o D\v{z}eroski and Peter Flach},
  address =      {Bled, Slovenia},
  month =        {June},
  series =       "Lecture Notes in Artificial Intelligence",
  number =       1634,
  pages =        "152-161",
  publisher =    {Springer-Verlag}
}

@InProceedings{ManDzeErj:Clog,
  author =       "Suresh Manandhar and Sa\v{s}o D\v{z}eroski 
                  and Toma\v{z} Erjavec",
  title =        "Learning Multilingual Morphology with {CLOG}",
  editor =       "David Page",
  booktitle =    "Inductive Logic Programming; 8th International
                  Workshop ILP-98, Proceedings",
  series =       "Lecture Notes in Artificial Intelligence",
  number =       1446,
  pages =        "135-144",
  publisher =    {Springer-Verlag},
  year =         "1998"
}

@article{er98,
        author = "Sa\v{s}o D\v{z}eroski and Toma\v{z} Erjavec",
        title =  "Inductive Learning of Multilingual Morphology",
        journal = "Electrotechnical Review",
        address = "Ljubljana, Slovenia",
        volume =  "65", 
        number =  "6", 
        pages =   "296-302",
        year =    "1998"
  }

@InProceedings{Alexin98-WAGA99:proc,
  author =       "Zolt{\'a}n Alexin and Szilvia Zvada and and Tibor
                 Gyim{\'o}thy",
  title =        "Application of {AGLEARN} on {H}ungarian
                 {P}art-of-speech {T}agging",
  booktitle =    "Second Workshop on Attribute Grammars and their
                 Applications, WAGA'99",
  year =         "1999",
  address =      "Amsterdam, The Netherlands",
  editor =       "D. Parigot and M. Mernik",
  publisher =    "INRIA rocquencourt",
  pages =        "133--152",
  month =        mar,
  mail =         "alexin@inf.u-szeged.hu,gyimi@inf.u-szeged.hu,zvada@inf.u-szeged.hu",
  abstract =     "In this paper we present an application of the AGLEARN
                 method to the part-of-speech (POS) tagging of Hungarian
                 sentences. The task of AGLEARN is to infer the semantic
                 functions associated with production. In the learning
                 process the grammar, the background semantic functions
                 and the examples can be used. We applied the AGLEARN
                 method to infer context rules to choose the correct
                 tags. A corpus with about 100 000 pre-tagged words has
                 been used for training and testing. By using AGLEARN
                 method learning data are generated to the C 4.5
                 attribute value learner. These generated data contain
                 information about the phrase structure of the
                 sentences. A background attribute grammar has been used
                 to determine these sructural information. Our
                 experinces showed that using this structural background
                 information C4.5 learner was able to infer more precise
                 context rules.",
  postscript =   "WAGA99/proceedings/alexin/alexin.ps",
  ppdf =         "WAGA99/proceedings/alexin/alexin.pdf",
  note =          "http://www-rocq.inria.fr/oscar/www/fnc2/WAGA99/accept.html",
}

@InProceedings{Horvath99-ILP99:proc,
  author =       "T. Horv{\'a}th and Zolt{\'a}n Alexin and Tibor Gyim{\'o}thy
                  and S. Wrobel",
  title =        "Application of {D}ifferent {L}earning {M}ethods to
                  {H}ungarian {P}art-of-speech {T}agging",
  booktitle =    "Proc. 9th Int. Conference on Inductive Logic
                  Programming, ILP99",
  pages =        {128-139},
  year =         1999,
  editor =       {Sa\v{s}o D\v{z}eroski and Peter Flach},
  address =      {Bled, Slovenia},
  month =        {June},
  number =       {1634},
  series =       {Lecture Notes in Artificial Intelligence},
  address =      "Bled, Slovenia"
}


%%%%%%%%%%Papers on the MULTEXT-East related Concede project:

  @InProceedings{complex99:cnc,
   author =      "Toma\v{z} Erjavec and Dan Tufi\c{s} and Tamas Varadi",
   title =       "Developing {TEI}-conformant Lexical Databases for {CEE}
                  Languages",
   booktitle =   "Proceedings of the 4th International Conference on 
                  Computational Lexicography, COMPLEX'99",
    year =       1999,
   pages =        "205-209",
   address =     "Pecs, Hungary"
  }

@InProceedings{lrec00:cnc,
  author =       "Toma\v{z} Erjavec and Roger Evans and Nancy Ide and
                  Adam Kilgarriff",
  title =        "The Concede Model for Lexical Databases",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"
}

@InProceedings{cnc-complex03,
  author = "Toma\v{z} Erjavec and Roger Evans and 
                  Nancy Ide and Adam Kilgarriff",
  title  = "{From Machine Readable Dictionaries to Lexical Databases: the Concede Experience}",
   booktitle =   "Proceedings of the 7th International Conference on 
                  Computational Lexicography, COMPLEX'03",
    year =       2003,
   pages =        "",
   address =     "Budapest, Hungary"
  }

%%%%%%%%%%Language Specific papers on MULTEXT-East resources:


@InProceedings{petkevic:orwl,
  author =       "Vladimir Petkevi\v{c}",
  title =        "{Czech translation of G. Orwell's '1984': Morphology and syntactic patterns in the corpus}",
  series =       "Lecture Notes in Artificial Intelligence",
  number =       1692,
  pages =        "77-82",
  year =         1999,
  publisher =    {Springer-Verlag}
}

@InProceedings{erk:mtelex,
  author =       "Toma\v{z} Erjavec",
  title =        "The {Multext-East Slovene Lexicon}",
  booktitle =    "Proceedings of the 7th Slovene Electrotechnical
                  Conference, ERK '98 ",
  pages =        "189-192",
  address =      "Portoro\v{z}, Slovenia",
  year =         1998,
  note = "http://nl.ijs.si/et/Bib/ERK98/"
}

@InProceedings{sdjt:fida,
  author = 	 "Toma\v{z} Erjavec and Vojko Gorjanc and Marko Stabej",
  title = 	 "Korpus {FIDA}",
  booktitle =	 "Proceedings of the Conference 'Language Technologies
		  for the Slovene Language'",
  organization = "Institute ``Jo\v{z}ef Stefan''",
  pages =        "124-127",
  address =      "Ljubljana, Slovenia",
  year =	 1998
}

@InProceedings{lrec00:rojckacic,
  author =       "Matej Rojc and Zdravko Ka\v{c}i\v{c}",
  title =        "A Computational Platform for Development of Morphologic and
                  Phonetic Lexica",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"
}

@InProceedings{lrec00:lat,
  author =       "Kristine Lev?ne and Andrejs Spektors",
  title =        "Morphemic Analysis and Morphological Tagging of
                  Latvian Corpus",
  booktitle =    "Second International Conference on Language Resources
                  and Evaluation, LREC'00",
  address =      "Athens",
  year =         2000,
  organization = "ELRA"

}