{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:56:33Z","timestamp":1743054993605,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":85,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642201271"},{"type":"electronic","value":"9783642201288"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-20128-8_1","type":"book-chapter","created":{"date-parts":[[2013,12,13]],"date-time":"2013-12-13T12:15:18Z","timestamp":1386936918000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Overviewing Important Aspects of the Last Twenty Years of Research in Comparable Corpora"],"prefix":"10.1007","author":[{"given":"Serge","family":"Sharoff","sequence":"first","affiliation":[]},{"given":"Reinhard","family":"Rapp","sequence":"additional","affiliation":[]},{"given":"Pierre","family":"Zweigenbaum","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,12,14]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Abdul Rauf, S., Schwenk, H.: Exploiting comparable corpora with TER and TERp. In: Proceedings of the 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora, pp. 46\u201354. Association for Computational Linguistics, Singapore (August 2009), http:\/\/www.aclweb.org\/anthology\/W\/W09\/W09-3109.pdf","DOI":"10.3115\/1690339.1690351"},{"key":"1_CR2","unstructured":"Adafre, S., de Rijke, M.: Finding similar sentences across multiple languages in Wikipedia. In: Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2006), pp. 62\u201369. Trento (2006)"},{"key":"1_CR3","unstructured":"Andrade, D., Matsuzaki, T., Tsujii, J.: Learning the optimal use of dependency-parsing information for finding translations with comparable corpora. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 10\u201318. Association for Computational Linguistics, Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1203"},{"key":"1_CR4","unstructured":"Babych, B., Hartley, A., Sharoff, S.: Translating from under-resourced languages: comparing direct transfer against pivot translation. In: Proceedings of the MT Summit XI, pp. 412\u2013418. Copenhagen (2007), http:\/\/corpus.leeds.ac.uk\/serge\/publications\/2007-mt-summit.pdf"},{"key":"1_CR5","unstructured":"Babych, B., Hartley, A., Sharoff, S., Mudraya, O.: Assisting translators in indirect lexical transfer. In: Proceedings of 45$$^{th}$$ ACL, pp. 739\u2013746. Prague (2007), http:\/\/corpus.leeds.ac.uk\/serge\/publications\/2007-ACL.pdf"},{"key":"1_CR6","unstructured":"Barbosa, L., Bangalore, S., Rangarajan Sridhar, V.K.: Crawling back and forth: using back and out links to locate bilingual sites. In: Proceedings of 5th International Joint Conference on Natural Language Processing, Chiang Mai (November 2011)"},{"key":"1_CR7","unstructured":"Baroni, M., Bernardini, S.: Bootcat: Bootstrapping corpora and terms from the Web. In: Proceedings of LREC2004. Lisbon (2004), http:\/\/sslmit.unibo.it\/baroni\/publications\/lrec2004\/bootcat_lrec_2004.pdf"},{"key":"1_CR8","unstructured":"Bel, N., Papavasiliou, V., Prokopidis, P., Toral, A., Arranz, V.: Mining and exploiting domain-specific corpora in the PANACEA platform. In: The 5th Workshop on Building and Using Comparable Corpora (2012)"},{"key":"1_CR9","unstructured":"Blancafort, H., Heid, U., Gornostay, T., M\u00e9choulam, C., Daille, B., Sharoff, S.: User-centred views on terminology extraction tools: usage scenarios and integration into MT and CAT tools. In: Proceedings TRALOGY Conference \"Translation Careers and Technologies: Convergence Points for the Future\" (2011)"},{"issue":"2","key":"1_CR10","first-page":"263","volume":"19","author":"P Brown","year":"1993","unstructured":"Brown, P., Pietra, S.D., Pietra, V.D., Mercer, R.: The mathematics of statistical machine translation: parameter estimation. Computat. Linguist. 19(2), 263\u2013312 (1993)","journal-title":"Computat. Linguist."},{"issue":"2","key":"1_CR11","first-page":"79","volume":"16","author":"PF Brown","year":"1990","unstructured":"Brown, P.F., Cocke, J., Jelinek, F., Lafferty, J.D., Mercer, R.L., Roossin, P.S.: A statistical approach to machine translation. Computat. Linguist. 16(2), 79\u201385 (1990)","journal-title":"Computat. Linguist."},{"key":"1_CR12","unstructured":"Budge, E.A.T.W.: The Rosetta Stone. British Museum. London (1913)"},{"key":"1_CR13","unstructured":"Chen, J., Nie, J.: Parallel Web text mining for cross-language ir. In: Proceedings of RIAO, pp. 62\u201377 (2000)"},{"key":"1_CR14","unstructured":"Chiao, Y.C., Sta, J.D., Zweigenbaum, P.: A novel approach to improve word translations extraction from non-parallel, comparable corpora. In: Proceedings International Joint Conference on Natural Language Processing, Hainan (2004)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Chiao, Y.C., Zweigenbaum, P.: Looking for candidate translational equivalents in specialized, comparable corpora. In: COLING 2002 (2002)","DOI":"10.3115\/1071884.1071904"},{"issue":"4","key":"1_CR16","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1075\/ijcl.13.4.04def","volume":"13","author":"B Defrancq","year":"2008","unstructured":"Defrancq, B.: Establishing cross-linguistic semantic relatedness through monolingual corpora. Int. J. Corpus Linguist. 13(4), 465\u2013490 (2008)","journal-title":"Int. J. Corpus Linguist."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"D\u00e9jean, H., Gaussier, E., Sadat, F.: An approach based on multilingual thesauri and model combination for bilingual lexicon extraction. In: COLING 2002 (2002)","DOI":"10.3115\/1072228.1072394"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Del\u00e9ger, L., Cartoni, B., Zweigenbaum, P.: Paraphrase detection in monolingual specialized\/lay comparable corpora. In: Sharoff, S., Rapp, R., Fung, P., Zweigenbaum, P. (eds.) Building and Using Comparable Corpora. Springer, Dordrecht (2012)","DOI":"10.1007\/978-3-642-20128-8_12"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Del\u00e9ger, L., Zweigenbaum, P.: Extracting lay paraphrases of specialized expressions from monolingual comparable medical corpora. In: Fung, P., Zweigenbaum, P., Rapp, R. (eds.) Proceedings of the 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-Parallel Corpora, pp. 2\u201310. Association for Computational Linguistics, Singapore (August 2009), http:\/\/aclweb.org\/anthology\/W\/W09\/W09-3102","DOI":"10.3115\/1690339.1690343"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Diab, M., Finch, S.: A statistical wordlevel translation model for comparable corpora. In: Proceedings of the Conference on Content-Based Multimedia Information Access (RIAO) (2000)","DOI":"10.21236\/ADA455144"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Dorow, B., Laws, F., Michelbacher, L., Scheible, C., Utt, J.: A graph-theoretic algorithm for automatic extension of translation lexicons. In: EACL 2009 Workshop on Geometrical Models of Natural Language Semantics (2009)","DOI":"10.3115\/1705415.1705427"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Eisele, A., Federmann, C., Saint-Amand, H., Jellinghaus, M., Herrmann, T., Chen, Y.: Using moses to integrate multiple rule-based machine translation engines into a hybrid system. In: Proceedings of the Third Workshop on Statistical Machine Translation at ACL2008, pp. 179\u2013182 (2008)","DOI":"10.3115\/1626394.1626422"},{"key":"1_CR23","unstructured":"Eisele, A., Chen, Y.: MultiUN: A multilingual corpus from United Nations documents. In: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC\u201910). Valletta, Malta (2010), http:\/\/www.euromatrixplus.net\/multi-un\/"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Elhadad, N., Sutaria, K.: Mining a lexicon of technical terms and lay equivalents. In: Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing, pp. 49\u201356. Association for Computational Linguistics (2007)","DOI":"10.3115\/1572392.1572402"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Enright, J., Kondrak, G.: A fast method for parallel document identification. In: NAACL \/ Human Language Technologies, pp. 29\u201332. Rochester (2007)","DOI":"10.3115\/1614108.1614116"},{"key":"1_CR26","doi-asserted-by":"crossref","first-page":"77","DOI":"10.2478\/v10108-010-0003-9","volume":"93","author":"M. Espl\u00e0-Gomis","year":"2010","unstructured":"Espl\u00e0-Gomis, M., Forcada, M.L.: Combining content-based and url-based heuristics to harvest aligned bitexts from multilingual sites with bitextor. Prague Bull. Math. Linguist. 93, 77\u201386 (2010)","journal-title":"Prague Bull. Math. Linguist."},{"key":"1_CR27","unstructured":"Fung, P.: Compiling bilingual lexicon entries from a non-parallel English-Chinese corpus. In: Proceedings of Third Annual Workshop on Very Large Corpora, pp. 173\u2013183. Boston (1995)"},{"issue":"1","key":"1_CR28","first-page":"99","volume":"12","author":"P Fung","year":"1998","unstructured":"Fung, P.: Extracting key terms from chinese and japanese texts. Int. J. Comput. Process. Orient. Lang. 12(1), 99\u2013121 (1998)","journal-title":"Int. J. Comput. Process. Orient. Lang."},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Fung, P.: A statistical view on bilingual lexicon extraction: from parallel corpora to non-parallel corpora. In: Machine Translation and the Information Soup, pp. 1\u201317. Springer, Berlin (1998), http:\/\/www.springerlink.com\/content\/pqkpwpw32f5r74ev\/","DOI":"10.1007\/3-540-49478-2_1"},{"key":"1_CR30","unstructured":"Fung, P., McKeown, K.: Finding terminology translations from non-parallel corpora. In: Proceedings of the 5th Annual Workshop on Very Large Corpora, pp. 192\u2013202 (1997)"},{"key":"1_CR31","unstructured":"Gahbiche-Braham, S., Bonneau-Maynard, H., Yvon, F.: Two ways to use a noisy parallel news corpus for improving statistical machine translation. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 44\u201351. Association for Computational Linguistics, Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1207"},{"issue":"1","key":"1_CR32","first-page":"75","volume":"19","author":"W Gale","year":"1993","unstructured":"Gale, W., Church, K.: A program for aligning sentences in bilingual corpora. Comput. linguist. 19(1), 75\u2013102 (1993)","journal-title":"Comput. linguist."},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Gamallo Otero, P., Garcia, M.: Extraction of bilingual cognates from wikipedia. In: Caseli, H., Villavicencio, A., Teixeira, A., Perdigo, F. (eds.) Computational Processing of the Portuguese Language. Lecture Notes in Artificial Intelligence, vol. 7243, pp. 63\u201372. Springer, Berlin (2012)","DOI":"10.1007\/978-3-642-28885-2_7"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Gamallo Otero, P., Pichel Campos, J.R.: An approach to acquire word translations from nonparallel texts. In: EPIA, pp. 600\u2013610 (2005)","DOI":"10.1007\/11595014_59"},{"key":"1_CR35","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1007\/978-3-642-12116-6_40","volume":"6008","author":"P. Gamallo Otero","year":"2010","unstructured":"Gamallo Otero, P., Pichel Campos, J.R.: Automatic generation of bilingual dictionaries using intermediary languages and comparable corpora. Comput. Linguist. Intell. Text Process. 6008, 473\u2013483 (2010)","journal-title":"Comput. Linguist. Intell. Text Process."},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Garera, N., Callison-Burch, C., Yarowsky, D.: Improving translation lexicon induction from monolingual corpora via dependency contexts and part-of-speech equivalences. In: CoNLL 09: Proceedings of the Thirteenth Conference on Computational Natural Language Learning, p. 129137. Morristown (2009)","DOI":"10.3115\/1596374.1596397"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Gaussier, E., Renders, J.M., Matveeva, I., Goutte, C., Djean, H.: A geometric view on bilingual lexicon extraction from comparable corpora. In: Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, p. 526533. Barcelona (2004)","DOI":"10.3115\/1218955.1219022"},{"key":"1_CR38","unstructured":"Germann, U.: Aligned Hansards of the 36th Parliament of Canada (2001), http:\/\/www.isi.edu\/natural-language\/download\/hansard\/"},{"key":"1_CR39","unstructured":"Haghighi, A., Liang, P., Berg-Kirkpatrick, T., Klein, D.: Learning bilingual lexicons from monolingual corpora. In: Proceedings of ACL-08: HLT, pp. 771\u2013779. Columbus (2008)"},{"issue":"23","key":"1_CR40","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"Z Harris","year":"1954","unstructured":"Harris, Z.: Distributional structure. Word 10(23), 146\u2013162 (1954)","journal-title":"Word"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Hassan, S., Mihalcea, R.: Cross-lingual semantic relatedness using encyclopedic knowledge. In: EMNLP (2009)","DOI":"10.3115\/1699648.1699665"},{"key":"1_CR42","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/978-3-642-28601-8_8","volume":"7182","author":"A Hazem","year":"2012","unstructured":"Hazem, A., Morin, E.: Qalign: a new method for bilingual lexicon extraction from comparable corpora. Comput. Linguist. Intell. Text Process. 7182, 83\u201396 (2012)","journal-title":"Comput. Linguist. Intell. Text Process."},{"key":"1_CR43","unstructured":"Hazem, A., Morin, E.: Extraction de lexiques bilingues partir de corpus comparables par combinaison de reprsentations contextuelles. In: Proceedings of the TALN 2013. ATALA, Les Sables d\u2019Olonne (2013), in Press"},{"key":"1_CR44","unstructured":"Hewavitharana, S., Vogel, S.: Extracting parallel phrases from comparable data. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 61\u201368. Association for Computational Linguistics, Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1209"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Ji, H.: Mining name translations from comparable corpora by creating bilingual information networks. In: Proceedings of the 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora, pp. 34\u201337. Association for Computational Linguistics, Singapore (August 2009), http:\/\/www.aclweb.org\/anthology\/W\/W09\/W09-3107","DOI":"10.3115\/1690339.1690349"},{"issue":"1","key":"1_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1075\/ijcl.6.1.01roc","volume":"6","author":"A Kilgarriff","year":"2001","unstructured":"Kilgarriff, A.: Comparing corpora. Int. J. Corpus Linguist. 6(1), 1\u201337 (2001)","journal-title":"Int. J. Corpus Linguist."},{"key":"1_CR47","unstructured":"Kilgarriff, A.: Comparable corpora within and across languages, word frequency lists and the kelly project. In: Proceedings of workshop on Building and Using Comparable Corpora at LREC, Malta (2010)"},{"key":"1_CR48","unstructured":"Knight, K., Megyesi, B., Schaefer, C.: The [copiale] cipher. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 2\u20139. Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1202"},{"key":"1_CR49","unstructured":"Koehn, P.: Europarl: a parallel corpus for statistical machine translation. In: Proceedings of MT Summit 2005 (2005), http:\/\/www.iccs.inf.ed.ac.uk\/ pkoehn\/publications\/europarl-mtsummit05.pdf"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Koehn, P., Knight, K.: Learning a translation lexicon from monolingual corpora. In: Proceedings of the ACL-02 workshop on Unsupervised lexical acquisition, pp. 9\u201316 (2002)","DOI":"10.3115\/1118627.1118629"},{"key":"1_CR51","unstructured":"Lahaussois, A., Guillaume, S.: A viewing and processing tool for the analysis of a comparable corpus of kiranti mythology. In: Proceedings of the 5th Workshop on Building and Using Comparable Corpora, pp. 33\u201341. ELDA, Istanbul (2012)"},{"key":"1_CR52","unstructured":"Langlais, P., Patry, A.: Translating unknown words by analogical learning. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 877\u2013886 (2007)"},{"key":"1_CR53","unstructured":"Li, B.: Measuring and improving comparable corpus quality. Ph.D. thesis, Universit de Grenoble, Grenoble (June 2012)"},{"key":"1_CR54","unstructured":"Michelbacher, L., Laws, F., Dorow, B., Heid, U.,, Sch\u00fctze, H.: Building a cross-lingual relatedness thesaurus using a graph similarity measure. In: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC\u201910), Valletta (2010)"},{"key":"1_CR55","unstructured":"Morin, E., Daille, B., Takeuchi, K., Kageura, K.: Bilingual terminology mining\u2014using brain, not brawn comparable corpora. In: Proceedings of the 45$$^{th}$$ Annual Meeting of the Association for Computational Linguistics, pp. 664-671. Prague, Czech Republic (2007)"},{"key":"1_CR56","unstructured":"Morin, E., Prochasson, E.: Bilingual lexicon extraction from comparable corpora enhanced with parallel corpora. In: BUCC2011 (2011)"},{"issue":"4","key":"1_CR57","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"DS Munteanu","year":"2005","unstructured":"Munteanu, D.S., Marcu, D.: Improving machine translation performance by exploiting non-parallel corpora. Comput. Linguist. 31(4), 477\u2013504 (2005)","journal-title":"Comput. Linguist."},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Munteanu, D., Marcu, D.: Extracting parallel sub-sentential fragments from non-parallel corpora. In: Proceedings of International Conference on Computational Linguistics and Association of Computational Linguistics, COLING-ACL 2006. Sydney (2006)","DOI":"10.3115\/1220175.1220186"},{"key":"1_CR59","unstructured":"Patry, A., Langlais, P.: Identifying parallel documents from a large bilingual collection of texts: Application to parallel article extraction in Wikipedia. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 87\u201395. Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1212"},{"issue":"4","key":"1_CR60","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s10590-007-9029-7","volume":"20","author":"V Pekar","year":"2006","unstructured":"Pekar, V., Mitkov, R., Blagoev, D., Mulloni, A.: Finding translations for low-frequency words in comparable corpora. Mach. Transl. 20(4), 247\u2013266 (2006)","journal-title":"Mach. Transl."},{"key":"1_CR61","unstructured":"Peters, C., Picchi, E.: Using linguistic tools and resources in cross-language retrieval. In: Hull, D., Oard, D. (eds.) Cross-Language Text and Speech Retrieval Papers from the 1997 AAAI Spring Symposium, pp. 179\u2013188. AAAI Press, San Francisco (1997)"},{"key":"1_CR62","unstructured":"Picchi, E., Peters, C.: Exploiting lexical resources and linguistic tools in cross-language information retrieval: the EuroSearch approach. In: First International Conference on Language Resources & Evaluation, pp. 865\u2013872. Granada (1998)"},{"key":"1_CR63","unstructured":"Prochasson, E., Fung, P.: Rare word translation extraction from aligned comparable documents. In: Proceedings of ACL-HLT, Portland (2011)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Rapp, R.: Identifying word translations in non-parallel texts. In: Proceedings of the 33rd ACL, pp. 320\u2013322. Cambridge (1995)","DOI":"10.3115\/981658.981709"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Rapp, R.: Automatic identification of word translations from unrelated English and German corpora. In: Proceedings of the 37th ACL, pp. 395\u2013398. Maryland (1999)","DOI":"10.3115\/1034678.1034756"},{"key":"1_CR66","unstructured":"Rapp, R., Sharoff, S., Babych, B.: Identifying word translations from comparable documents without a seed lexicon. In: Proceedings of the Eighth Language Resources and Evaluation Conference, LREC 2012. Istanbul (2012)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Rapp, R., Zock, M.: Automatic dictionary expansion using non-parallel corpora. In: Fink, A., Lausen, B., Ultsch, W.S.A. (eds.) Advances in Data Analysis, Data Handling and Business Intelligence. Proceedings of the 32nd Annual Meeting of the GfKl, 2008. Springer, Heidelberg (2010)","DOI":"10.1007\/978-3-642-01044-6_29"},{"key":"1_CR68","unstructured":"Rapp, R., Zock, M.: The noisier the better: identifying multilingual word translations using a single monolingual corpus. In: Proceedings of the 4th International Workshop on Cross Lingual Information Access at COLING. pp. 16\u201325. Beijing (2010)"},{"issue":"3","key":"1_CR69","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1162\/089120103322711578","volume":"29","author":"P. Resnik","year":"2003","unstructured":"Resnik, P., Smith, N.: The Web as a parallel corpus. Comput. Linguist. 29(3), 349\u2013380 (2003), http:\/\/www.umiacs.umd.edu\/ resnik\/strand\/","journal-title":"Comput. Linguist."},{"key":"1_CR70","unstructured":"Robitaille, X., Sasaki, Y., Tonoike, M., Sato, S., Utsuro, T.: Compiling French-Japanese terminologies from the Web. In: Proceedings of the 11st Conference of the European Chapter of the Association for Computational Linguistics, pp. 225\u2013232. Trento (2006)"},{"key":"1_CR71","unstructured":"Rosset, S., Grouin, C., Fort, K., Galibert, O., Kahn, J., Zweigenbaum, P.: Structured named entities in two distinct press corpora: contemporary broadcast news and old newspapers. In: Proceedings of the Sixth Linguistic Annotation Workshop, pp. 40\u201348. Association for Computational Linguistics, Jeju, Republic of Korea (July 2012), http:\/\/www.aclweb.org\/anthology\/W12-3606"},{"key":"1_CR72","doi-asserted-by":"crossref","unstructured":"Schafer, C., Yarowsky, D.: Inducing translation lexicons via diverse similarity measures and bridge languages. In: Proceedings of CoNLL (2002)","DOI":"10.3115\/1118853.1118879"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Segouat, J., Braffort, A.: Toward categorization of sign language corpora. In: Proceedings of the 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora, pp. 64\u201367. Association for Computational Linguistics, Singapore (August 2009), http:\/\/www.aclweb.org\/anthology\/W\/W09\/W09-3111","DOI":"10.3115\/1690339.1690354"},{"key":"1_CR74","unstructured":"Sharoff, S.: Creating general-purpose corpora using automated search engine queries. In: Baroni, M., Bernardini, S. (eds.) WaCky! Working Papers on the Web as Corpus. Gedit, Bologna (2006), http:\/\/wackybook.sslmit.unibo.it"},{"key":"1_CR75","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-90-481-9178-9_7","volume-title":"Genres on the Web: Computational Models and Empirical Studies","author":"S Sharoff","year":"2010","unstructured":"Sharoff, S.: In the garden and in the jungle: comparing genres in the BNC and Internet. In: Mehler, A., Sharoff, S., Santini, M. (eds.) Genres on the Web: Computational Models and Empirical Studies, pp. 149\u2013166. Springer, Berlin (2010)"},{"key":"1_CR76","unstructured":"Shezaf, D., Rappoport, A.: Bilingual lexicon generation using non-aligned signatures. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. p. 98107. Uppsala (2010)"},{"key":"1_CR77","unstructured":"Skadi\u0146a, I., Vasi\u013cjevs, A., Skadi\u0146\u0161, R., Gaizauskas, R., Tufi\u015f, D., Gornostay, T.: Analysis and evaluation of comparable corpora for under resourced areas of machine translation. In: Proc. 3rd Workshop on Building and Using Comparable Corpora. Malta (2010)."},{"key":"1_CR78","doi-asserted-by":"crossref","unstructured":"Tanaka, K., Iwasaki, H.: Extraction of lexical translations from non-aligned corpora. In: Proceedings of the 16th conference on Computational linguistics (COLING96), vol. 2, pp. 580\u2013585 (1996)","DOI":"10.3115\/993268.993270"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Tillmann, C.: A beam-search extraction algorithm for comparable data. In: Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pp. 225\u2013228 (2009)","DOI":"10.3115\/1667583.1667653"},{"key":"1_CR80","unstructured":"Tsvetkov, Y., Wintner, S.: Automatic acquisition of parallel corpora from websites with dynamic content. In: Proceedings of The Seventh International Conference on, Language Resources and Evaluation (LREC-2010) (2010)"},{"key":"1_CR81","unstructured":"Uszkoreit, J., Ponte, J.M., Popat, A.C., Dubiner, M.: Large scale parallel document mining for machine translation. In: COLING \u201910: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 1101\u20131109 (2010)"},{"key":"1_CR82","doi-asserted-by":"crossref","unstructured":"Varga, D., Halacsy, P., Kornai, A., Nagy, V., Nemeth, L., Tron, V.: Parallel corpora for medium density languages. In: N. Nicolov, K. Bontcheva, G.A., Mitkov, R. (eds.) Recent Advances in Natural Language Processing IV. Selected papers from RANLP-05, pp. 247\u2013258. Benjamins (2007), http:\/\/www.kornai.com\/Papers\/ranlp05parallel.pdf","DOI":"10.1075\/cilt.292.32var"},{"key":"1_CR83","unstructured":"Wang, R., Callison-Burch, C.: Paraphrase fragment extraction from monolingual comparable corpora. In: Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web, pp. 52\u201360. Association for Computational Linguistics, Portland (June 2011), http:\/\/www.aclweb.org\/anthology\/W11-1208"},{"key":"1_CR84","doi-asserted-by":"crossref","unstructured":"Yu, K., Tsujii, J.: Extracting bilingual dictionary from comparable corpora with dependency heterogeneity. In: Proceedings of HLT-NAACL 2009, pp. 121\u2013124. Boulder (2009)","DOI":"10.3115\/1620853.1620888"},{"key":"1_CR85","unstructured":"Zhao, B., Vogel, S.: Adaptive parallel sentences mining from Web bilingual news collection. In: Proceeding of the 2002 IEEE International Conference on Data Mining (ICDM 2002) (2002)"}],"container-title":["Building and Using Comparable Corpora"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-20128-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T23:37:42Z","timestamp":1688859462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-20128-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642201271","9783642201288"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-20128-8_1","relation":{},"subject":[],"published":{"date-parts":[[2013]]},"assertion":[{"value":"14 December 2013","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}