{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:11:42Z","timestamp":1769040702499,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,8,29]],"date-time":"2014-08-29T00:00:00Z","timestamp":1409270400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1007\/s10579-014-9277-0","type":"journal-article","created":{"date-parts":[[2014,8,28]],"date-time":"2014-08-28T09:21:25Z","timestamp":1409217685000},"page":"679-707","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["An overview of the European Union\u2019s highly multilingual parallel corpora"],"prefix":"10.1007","volume":"48","author":[{"given":"Ralf","family":"Steinberger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Ebrahim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Poulis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Carrasco-Benitez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Schl\u00fcter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marek","family":"Przybyszewski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Signe","family":"Gilbro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,8,29]]},"reference":[{"key":"9277_CR1","unstructured":"Balahur, A., Steinberger, R., Kabadjov, M., Zavarella, V., van der Goot, E., Halkia, M., et al. (2010). Sentiment analysis in the news. In Proceedings of the 7th international conference on language resources and evaluation (LREC\u20192010), Valletta, Malta, 19\u201321 May 2010, pp. 2216\u20132220."},{"key":"9277_CR2","unstructured":"Carrasco-Benitez, M. T. (2008). Open architecture for multilingual parallel texts. http:\/\/arxiv.org\/ftp\/arxiv\/papers\/0808\/0808.3889.pdf ."},{"key":"9277_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Kay, M., & Eisele A. (2009). Intersecting multilingual data for faster and better statistical translations. In Proceedings of human language technologies: The 2009 annual conference of the North American chapter of the association for computational linguistics, Boulder, Colorado, pp. 128\u2013136.","DOI":"10.3115\/1620754.1620773"},{"key":"9277_CR4","unstructured":"Chiao, Y.-C., Kraif, O., Laurent, D., Nguyen, T. M. H., Semmar, N., Stuck, F., et al. (2006). Evaluation of multilingual text alignment systems: The ARCADE II project. In Proceedings of the 5th international conference on language resources and evaluation (LREC\u20192006), Genoa, Italy, pp. 1975\u20131978."},{"key":"9277_CR5","unstructured":"Cohn T., & Lapata, M. (2007). Machine translation by triangulation: Making effective use of multi-parallel corpora. In Proceedings of the 45th annual meeting of the association for computational linguistics, Prague, Czech Republic, pp. 728\u2013735."},{"key":"9277_CR6","unstructured":"EC&DGT (2008). European Commission & Directorate General for Translation\u2014Translation tools and workflow. Office for Official Publications, Brussels, Belgium."},{"key":"9277_CR7","unstructured":"Ehrmann, M., Turchi, M., & Steinberger, R. (2011). Building a multilingual named entity-annotated corpus. In Proceedings of the 8th international conference recent advances in natural language processing (RANLP\u20192011), Hissar, Bulgaria."},{"key":"9277_CR8","unstructured":"Eisele A., & Chen, Y. (2010). MultiUN: A Multilingual Corpus from United Nation Documents. In Proceedings of the international conference on language resources and evaluation (LREC 2010), Valletta, Malta, pp. 2868\u20132872."},{"key":"9277_CR9","unstructured":"Erjavec, T. (2010). MULTEXT-East version 4: Multilingual morphosyntactic specifications, lexicons and corpora. In Proceedings of the seventh international conference on language resources and evaluation (LREC), Valletta, Malta, pp. 2544\u20132547."},{"key":"9277_CR10","unstructured":"Erjavec T., & Ide, N. (1998). The MULTEXT-East corpus. In Proceedings of the first international conference on language resources and evaluation (LREC), Granada, Spain."},{"issue":"1","key":"9277_CR11","first-page":"75","volume":"19","author":"W Gale","year":"1993","unstructured":"Gale, W., & Church, K. (1993). A program for aligning sentences in bilingual corpora. Computational Linguistics, 19(1), 75\u2013102.","journal-title":"Computational Linguistics"},{"key":"9277_CR12","unstructured":"Hajlaoui, N., Kolovratnik, D., V\u00e4yrynen, J., Varga, D., & Steinberger, R. (2014). DCEP\u2014Digital Corpus of the European Parliament. In Proceedings of the 9th edition of its language resources and evaluation conference, Reykjavik, Iceland."},{"key":"9277_CR38","doi-asserted-by":"crossref","unstructured":"Ide N., & V\u00e9ronis, J. (1994). MULTEXT: Multilingual text tools and corpora. In Proceedings of the 15th international conference on computational linguistics (CoLing), Kyoto, Japan, pp. 588\u2013592.","DOI":"10.3115\/991886.991990"},{"key":"9277_CR13","unstructured":"Koehn, P. (2005). EuroParl: A parallel corpus for statistical machine translation. In Proceedings of the machine translation summit, Phuket, Thailand, pp. 79\u201386."},{"key":"9277_CR14","unstructured":"Koehn, P., Birch, A., & Steinberger, R. (2009). 462 Machine Translation Systems for Europe. In L. Gerber, P. Isabelle, R. Kuhn, N. Bemish, M. Dillinger, & M.-J. Goulet (Eds.), Proceedings of the twelfth machine translation summit (MT-Summit XII), Ottawa, Canada, August 2009, pp. 65\u201372."},{"key":"9277_CR15","doi-asserted-by":"crossref","unstructured":"Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., et al. (2007). Moses: Open source toolkit for statistical machine translation. In Proceedings of the annual meeting of the association for computational linguistics (ACL), demonstration session, Prague, Czech Republic, June 2007.","DOI":"10.3115\/1557769.1557821"},{"key":"9277_CR16","unstructured":"Lardilleux, A., & Lepage, Y. (2009). Sampling-based multilingual alignment. In International conference on recent advances in natural language processing (RANLP\u20192009), Borovets, Bulgaria, pp. 214\u2013218."},{"key":"9277_CR17","unstructured":"Lefever, E., & Hoste, V. (2010). SemEval-2010 task 3: Cross-lingual word sense disambiguation. In Proceedings of the 5th international workshop on semantic evaluation (SemEval\u20192010), Uppsala, Sweden, pp. 15\u201320."},{"key":"9277_CR18","unstructured":"Landauer T., & Littman, M. (1991). A statistical method for language-independent representation of the topical content of text segments. In Proceedings of the 11th international conference \u2018Expert Systems and Their Applications\u2019, Vol. 8, pp. 77\u201385."},{"key":"9277_CR19","unstructured":"Mehdad Y., Negri, M., & Federico, M. (2010). Towards cross-lingual textual entailment. In Proceedings of human language technologies, Los Angeles, CA, USA, pp. 321\u2013324."},{"key":"9277_CR20","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1613\/jair.2843","volume":"36","author":"T Naseem","year":"2009","unstructured":"Naseem, T., Snyder, B., Eisenstein, J., & Barzilay, R. (2009). Multilingual part-of-speech tagging: Two unsupervised approaches. Journal of Artificial Intelligence, 36, 341\u2013385.","journal-title":"Journal of Artificial Intelligence"},{"issue":"1","key":"9277_CR21","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1162\/089120103321337421","volume":"29","author":"FJ Och","year":"2003","unstructured":"Och, F. J., & Ney, H. (2003). A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1), 19\u201351.","journal-title":"Computational Linguistics"},{"key":"9277_CR22","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1613\/jair.2863","volume":"36","author":"S Pad\u00f3","year":"2009","unstructured":"Pad\u00f3, S., & Lapata, M. (2009). Cross-lingual annotation projection of semantic roles. Journal of Artificial Intelligence Research, 36, 307\u2013340.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9277_CR23","doi-asserted-by":"crossref","unstructured":"Potthast, M., Barr\u00f3n-Cede\u00f1o, A., Stein, B., & Rosso, P. (2011). Cross-language plagiarism detection. In Language resources and evaluation. Special issue on plagiarism and authorship analysis, Vol. 45, no. 1, pp. 45\u201362.","DOI":"10.1007\/s10579-009-9114-z"},{"issue":"1\u20132","key":"9277_CR24","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1023\/A:1001798929185","volume":"33","author":"P Resnik","year":"1999","unstructured":"Resnik, P., Olsen, M. B., & Diab, M. (1999). The Bible as a parallel corpus: Annotating the \u2018Book of 2000 Tongues\u2019. Computers and the Humanities, 33(1\u20132), 129\u2013153.","journal-title":"Computers and the Humanities"},{"key":"9277_CR25","doi-asserted-by":"crossref","unstructured":"Steinberger, R. (2011). A survey of methods to ease the development of highly multilingual Text Mining applications. Language Resources and Evaluation Journal, 46(2), 155\u2013176.","DOI":"10.1007\/s10579-011-9165-9"},{"key":"9277_CR26","unstructured":"Steinberger, R. (2013). Multilingual and cross-lingual news analysis in the Europe Media Monitor (EMM). In M. Lupu, E. Kanoulas, & F. Loizides (Eds.), Multidisciplinary information retrieval. 6th information retrieval facility conference (IRFC\u20192013), Limassol, Cyprus. Springer Lecture Notes in Computer Science, Vol. 8201, pp. 1\u20134."},{"key":"9277_CR27","unstructured":"Steinberger, R., Ebrahim, M., & Turchi, M. (2012a). JRC EuroVoc Indexer JEX\u2014A freely available multi-label categorisation tool. In Proceedings of the 8th international conference on language resources and evaluation (LREC\u20192012), Istanbul, 21\u201327 May 2012."},{"key":"9277_CR28","unstructured":"Steinberger, R., Eisele, A., Klocek, S., Pilos, S., & Schl\u00fcter, P. (2012b). DGT-TM: A freely available translation memory in 22 languages. In Proceedings of the 8th international conference on language resources and evaluation (LREC\u20192012), Istanbul, 21\u201327 May 2012, pp. 454\u2013459."},{"key":"9277_CR29","unstructured":"Steinberger, J., Lenkova, P., Kabadjov, M., Steinberger, R., & van der Goot, E. (2011a). Multilingual entity-centered sentiment analysis evaluated by parallel corpora. In Proceedings of the 8th international conference recent advances in natural language processing (RANLP\u20192011), Hissar, Bulgaria, 12\u201314 September 2011."},{"key":"9277_CR30","unstructured":"Steinberger, R., Pouliquen, B., Kabadjov, M., & van der Goot, E. (2011b). JRC-Names: A freely available, highly multilingual named entity resource. In Proceedings of the 8th international conference recent advances in natural language processing (RANLP\u20192011), Hissar, Bulgaria, 12\u201314 September 2011, pp. 104\u2013110."},{"key":"9277_CR31","unstructured":"Steinberger, R., Pouliquen, B., & van der Goot, E. (2009). An Introduction to the Europe media monitor family of applications. In F. Gey, N. Kando, & J. Karlgren (Eds.), Information access in a multilingual world\u2014proceedings of the SIGIR 2009 workshop (SIGIR-CLIR\u20192009), Boston, USA, 23 July 2009, pp. 1\u20138."},{"key":"9277_CR32","unstructured":"Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufi\u015f, D., et al. (2006). The JRC-Acquis: A multilingual aligned parallel corpus with 20\u00a0+\u00a0languages. In Proceedings of the 5th international conference on language resources and evaluation (LREC\u20192006), Genoa, Italy, 24\u201326 May 2006, pp. 2142\u20132147."},{"key":"9277_CR33","doi-asserted-by":"crossref","unstructured":"Tiedemann, J. (2009). News from OPUS\u2014A collection of multilingual parallel corpora with tools and interfaces. In Recent advances in natural language processing (Vol. V, pp. 237\u2013248). John Benjamins, Amsterdam\/Philadelphia.","DOI":"10.1075\/cilt.309.19tie"},{"key":"9277_CR34","unstructured":"Tiedemann, J., & Nygaard, L. (2004). The OPUS corpus\u2014Parallel and free. In Proceedings of the 4th international conference on language resources an evaluation (LREC), Lisbon, Portugal, pp. 1183\u20131186."},{"key":"9277_CR35","unstructured":"Tufi\u015f, D. (2004). Term translations in parallel corpora: Discovery and consistency check. In Proceedings of the 4th international conference on language resources an evaluation (LREC), Lisbon, Portugal, pp. 1981\u20131984."},{"key":"9277_CR36","doi-asserted-by":"crossref","unstructured":"Turchi, M., Steinberger, J., Kabadjov, M. & Steinberger, R. (2010). Using parallel corpora for multilingual (multi-document) summarisation evaluation. Multilingual and multimodal information access evaluation. Springer Lecture Notes for Computer Science, LNCS 6360\/2010, pp. 52\u201363.","DOI":"10.1007\/978-3-642-15998-5_7"},{"key":"9277_CR37","unstructured":"Varga, D., Hal\u00e1csy, P., Kornai, A., Nagy, V., N\u00e9meth, L., & Tr\u00f3n, V. (2005). Parallel corpora for medium density languages. In Proceedings of RANLP\u20192005, Borovets, Bulgaria, pp. 590\u2013596."},{"key":"9277_CR39","unstructured":"Vinokourov, A., Shawe-Taylor, J., & Cristianini, N. (2003). Inferring a semantic representation of text via cross-language correlation analysis: Advances in neural information processing systems 15. In S. Becker, S. Thrun & K. Obermayer (Eds), (pp. 1473\u20131480). Cambridge, MA: MIT Press."},{"issue":"2008","key":"9277_CR40","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.dss.2007.07.008","volume":"45","author":"C-P Wei","year":"2008","unstructured":"Wei, C.-P., Yang, C. C., & Lin, C.-M. (2008). A Latent Semantic Indexing-based approach to multilingual document clustering. Decision Support Systems, 45(2008), 606\u2013620.","journal-title":"Decision Support Systems"},{"key":"9277_CR41","doi-asserted-by":"crossref","unstructured":"Yarowsky, D., Ngai, G., & Wicentowski, R. (2001) Inducing multilingual text analysis tools via robust projection across aligned corpora. In Proceedings of HLT\u201901, San Diego.","DOI":"10.3115\/1072133.1072187"},{"key":"9277_CR42","doi-asserted-by":"crossref","unstructured":"Zhechev, V., & Way, A. (2008). Automatic generation of parallel treebanks. In Proceedings of the 22nd international conference on computational linguistics (CoLing\u20192008), Manchester, UK, Vol. 1, pp. 1105\u20131112.","DOI":"10.3115\/1599081.1599220"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-014-9277-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-014-9277-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-014-9277-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,14]],"date-time":"2019-08-14T11:34:47Z","timestamp":1565782487000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-014-9277-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,8,29]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["9277"],"URL":"https:\/\/doi.org\/10.1007\/s10579-014-9277-0","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,8,29]]}}}