{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:30:42Z","timestamp":1778758242381,"version":"3.51.4"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,12,3]],"date-time":"2014-12-03T00:00:00Z","timestamp":1417564800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2015,3]]},"DOI":"10.1007\/s10579-014-9282-3","type":"journal-article","created":{"date-parts":[[2014,12,2]],"date-time":"2014-12-02T12:53:23Z","timestamp":1417524803000},"page":"147-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Domain adaptation of statistical machine translation with domain-focused web crawling"],"prefix":"10.1007","volume":"49","author":[{"given":"Pavel","family":"Pecina","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Toral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vassilis","family":"Papavassiliou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prokopis","family":"Prokopidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ale\u0161","family":"Tamchyna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Way","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"van Genabith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,12,3]]},"reference":[{"key":"9282_CR1","volume-title":"Focused crawler software package","author":"A Ard\u00f6","year":"2007","unstructured":"Ard\u00f6, A., & Golub, K. (2007). Focused crawler software package. Sweden: Tech. rep., Department of Information Technology, Lund University."},{"key":"9282_CR2","unstructured":"Axelrod, A., He, X., & Gao, J. (2011). Domain adaptation via pseudo in-domain data selection. In Proceedings of the conference on empirical methods in natural language processing. Edinburgh, United Kingdom, pp. 355\u2013362."},{"key":"9282_CR3","unstructured":"Banerjee, P., Du, J., Li, B., Naskar, S., Way, A., & van Genabith, J. (2010). Combining multi-domain statistical machine translation models using automatic classifiers. In Proceedings of the ninth conference of the association for machine translation in the Americas. Denver, Colorado, USA, pp. 141\u2013150."},{"key":"9282_CR4","unstructured":"Banerjee, P., Naskar, S.K., Roturier, J., Way, A., & van Genabith, J. (2011). Domain adaptation in statistical machine translation of user-forum data using component level mixture modelling. In Proceedings of the machine translation summit XIII. Xiamen, China, pp. 285\u2013292."},{"key":"9282_CR5","unstructured":"Banerjee, P., Rubino, R., Roturier, J., & van Genabith, J. (2013). Quality estimation-guided data selection for domain adaptation of smt. In Proceedings of the XIV machine translation summit. Nice, France, pp. 101\u2013108."},{"key":"9282_CR6","unstructured":"Barbosa, L., Rangarajan Sridhar, V.K., Yarmohammadi, M., & Bangalore, S. (2012). Harvesting parallel text in multiple languages with limited supervision. In Proceedings of the 24th international conference on computational linguistics. Mumbai, India, pp. 201\u2013214."},{"key":"9282_CR7","unstructured":"Baroni, M., Kilgarriff, A., Pomik\u00e1lek, J., & Rychl\u00fd, P. (2006). WebBootCaT: Instant domain-specific corpora to support human translators. In Proceedings of the 11th annual conference of the european association for machine translation. Oslo, Norway, pp. 47\u2013252."},{"issue":"3","key":"9282_CR8","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s10579-009-9081-4","volume":"43","author":"M Baroni","year":"2009","unstructured":"Baroni, M., Bernardini, S., Ferraresi, A., & Zanchetta, E. (2009). The WaCky Wide Web: A collection of very large linguistically processed web-crawled corpora. Language Resources and Evaluation, 43(3), 209\u2013226.","journal-title":"Language Resources and Evaluation"},{"key":"9282_CR9","doi-asserted-by":"crossref","unstructured":"Bergmark, D., Lagoze, C., & Sbityakov, A. (2002). Focused crawls, tunneling, and digital libraries. In M. Agosti & C. Thanos (Eds.), Research and advanced technology for digital libraries, lecture notes in computer science. Berlin: Heidelberg, Vol. 2458, pp. 49\u201370.","DOI":"10.1007\/3-540-45747-X_7"},{"key":"9282_CR10","doi-asserted-by":"crossref","unstructured":"Bertoldi, N., & Federico, M. (2009). Domain adaptation for statistical machine translation with monolingual resources. In Proceedings of the fourth workshop on statistical machine translation. Athens, Greece, pp. 182\u2013189.","DOI":"10.3115\/1626431.1626468"},{"key":"9282_CR11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.2478\/v10108-009-0011-9","volume":"91","author":"N Bertoldi","year":"2009","unstructured":"Bertoldi, N., Haddow, B., & Fouet, J. B. (2009). Improved minimum error rate training in Moses. The Prague Bulletin of Mathematical Linguistics, 91, 7\u201316.","journal-title":"The Prague Bulletin of Mathematical Linguistics"},{"key":"9282_CR12","unstructured":"Bisazza, A., Ruiz, N., & Federico, M. (2011). Fill-up versus interpolation methods for phrase-based SMT adaptation. In Proceedings of the international workshop on spoken language translation. San Francisco, California, USA, pp. 136\u2013143."},{"key":"9282_CR13","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems, 30, 107\u2013117.","journal-title":"Computer Networks and ISDN Systems"},{"key":"9282_CR14","unstructured":"Carpuat, M., & Wu, D. (2007). Improving statistical machine translation using word sense disambiguation. In Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning. Prague, Czech Republic, pp. 61\u201372."},{"key":"9282_CR15","unstructured":"Carpuat, M., Daum\u00e9 III, H., Fraser, A., Quirk, C., Braune, F., Clifton, A., et al. (2012). Domain adaptation in machine translation: Final report. In 2012 Johns Hopkins summer workshop final report. Baltimore, MD: Johns Hopkins University."},{"key":"9282_CR16","unstructured":"Chen, J., Chau, R., & Yeh, C.H. (2004). Discovering parallel text from the World Wide Web. In Proceedings of the 2nd workshop on Australasian information security, data mining and web intelligence, and software internationalisation. Darlinghurst, Australia, Vol. 32, pp. 157\u2013161."},{"key":"9282_CR17","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/S0169-7552(98)00108-1","volume":"30","author":"J Cho","year":"1998","unstructured":"Cho, J., Garcia-Molina, H., & Page, L. (1998). Efficient crawling through URL ordering. Computer Networks and ISDN Systems, 30, 161\u2013172.","journal-title":"Computer Networks and ISDN Systems"},{"key":"9282_CR18","unstructured":"Daum\u00e9 III, & H., Jagarlamudi, J. (2011). Domain adaptation for machine translation by mining unseen words. In Proceedings of the 49th annual meeting of the association for computational linguistics and human language technologies, short papers. Portland, Oregon, USA, pp. 407\u2013412."},{"key":"9282_CR19","unstructured":"D\u00e9silets, A., Farley, B., Stojanovic, M., & Patenaude, G. (2008). WeBiText: Building large heterogeneous translation memories from parallel web content. In Proceedings of translating and the computer. London, UK, Vol. 30, pp. 27\u201328."},{"key":"9282_CR20","unstructured":"Dorado, I. G. (2008). Focused crawling: Algorithm survey and new approaches with a manual analysis. Master\u2019s thesis, Department of Electro and Information Technology. Sweden: Lund University."},{"key":"9282_CR21","doi-asserted-by":"crossref","unstructured":"Dziwi\u0144ski, P., & Rutkowska, D. (2008). Ant focused crawling algorithm. In Proceedings of the 9th international conference on artificial intelligence and soft computing. Zakopane, Poland: Springer, pp. 1018\u20131028.","DOI":"10.1007\/978-3-540-69731-2_96"},{"key":"9282_CR22","unstructured":"Eck, M., Vogel, S., & Waibel, A. (2004). Language model adaptation for statistical machine translation based on information retrieval. In Proceedings of the international conference on language resources and evaluation. Lisbon, Portugal, pp. 327\u2013330."},{"key":"9282_CR23","first-page":"77","volume":"93","author":"M Espl\u00e0-Gomis","year":"2010","unstructured":"Espl\u00e0-Gomis, M., & Forcada, M. L. (2010). Combining content-based and URL-based heuristics to harvest aligned bitexts from multilingual sites with Bitextor. The Prague Bulletin of Mathemathical Lingustics, 93, 77\u201386.","journal-title":"The Prague Bulletin of Mathemathical Lingustics"},{"key":"9282_CR24","doi-asserted-by":"crossref","unstructured":"Finch, A., & Sumita, E. (2008). Dynamic model interpolation for statistical machine translation. In Proceedings of the third workshop on statistical machine translation. Columbus, Ohio, USA, pp. 208\u2013215.","DOI":"10.3115\/1626394.1626428"},{"key":"9282_CR25","unstructured":"Flournoy, R., & Duran, C. (2009). Machine translation and document localization at Adobe: From pilot to production. In Proceedings of the twelfth machine translation summit. Ottawa, Ontario, Canada, pp. 425\u2013428."},{"key":"9282_CR27","unstructured":"Foster, G., Goutte, C., & Kuhn, R. (2010). Discriminative instance weighting for domain adaptation in statistical machine translation. In Proceedings of the 2010 conference on empirical methods in natural language processing. Cambridge, Massachusetts, USA, pp. 451\u2013459."},{"key":"9282_CR26","doi-asserted-by":"crossref","unstructured":"Foster, G., & Kuhn, R. (2007). Mixture-model adaptation for SMT. In Proceedings of the second workshop on statistical machine translation. Prague, Czech Republic, pp. 128\u2013135.","DOI":"10.3115\/1626355.1626372"},{"key":"9282_CR28","first-page":"9","volume":"6","author":"Z Gao","year":"2010","unstructured":"Gao, Z., Du, Y., Yi, L., Yang, Y., & Peng, Q. (2010). Focused web crawling based on incremental learning. Journal of Computational Information Systems, 6, 9\u201316.","journal-title":"Journal of Computational Information Systems"},{"key":"9282_CR29","unstructured":"Haddow, B. (2013). Applying pairwise ranked optimisation to improve the interpolation of translation models. In Proceedings of the 2013 conference of the North American chapter of the association for computational linguistics: Human language technologies. Atlanta, Georgia, pp. 342\u2013347."},{"key":"9282_CR30","unstructured":"He, Y., Ma, Y., Roturier, J., Way, A., & van Genabith, J. (2010). Improving the post-editing experience using translation recommendation: A user study. In Proceedings of the ninth conference of the association for machine translation in the Americas. Denver, Colorado, USA, pp. 247\u2013256."},{"key":"9282_CR31","unstructured":"Hildebrand, A.S., Eck, M., Vogel, S., & Waibel, A. (2005). Adaptation of the translation model for statistical machine translation based on information retrieval. In Proceedings of the 10th annual conference of the European association for machine translation. Budapest, Hungary, pp. 133\u2013142."},{"key":"9282_CR32","unstructured":"Johnson, H., Martin, J.D., Foster, G.F., & Kuhn, R. (2007). Improving translation quality by discarding most of the phrasetable. In Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning. Prague, Czech Republic, pp. 967\u2013975."},{"issue":"3","key":"9282_CR33","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1162\/089120103322711569","volume":"29","author":"A Kilgarriff","year":"2003","unstructured":"Kilgarriff, A., & Grefenstette, G. (2003). Introduction to the special issue on the Web as corpus. Computational Linguistics, 29(3), 333\u2013348.","journal-title":"Computational Linguistics"},{"key":"9282_CR34","doi-asserted-by":"crossref","unstructured":"Kneser, R., & Ney, H. (1995). Improved backing-off for N-gram language modeling. In Proceedings of the international conference on acoustics. Speech and signal processing. pp. 181\u2013184.","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"9282_CR35","unstructured":"Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 conference on empirical methods in natural language processing. Barcelona, Spain, pp. 388\u2013395."},{"key":"9282_CR36","unstructured":"Koehn, P. (2005). Europarl: A parallel corpus for statistical machine translation. In Conference proceedings of the tenth machine translation summit. Phuket, Thailand, pp. 79\u201386."},{"key":"9282_CR37","unstructured":"Koehn, P., & Haddow, B. (2012). Interpolated backoff for factored translation models. In Proceedings of the tenth biennial conference of the association for machine translation in the Americas. San Diego, CA, USA."},{"key":"9282_CR38","doi-asserted-by":"crossref","unstructured":"Koehn, P., & Schroeder, J. (2007). Experiments in domain adaptationfor statistical machine translation. In Proceedings of the second workshop on statistical machine translation. Prague, Czech Republic, pp. 224\u2013227.","DOI":"10.3115\/1626355.1626388"},{"key":"9282_CR39","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 45th annual meeting of the ACL on interactive poster and demonstration sessions (pp. 177\u2013180). Prague: Czech Republic."},{"key":"9282_CR40","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C., Fankhauser, P., & Nejdl, W. (2010). Boilerplate detection using shallow text features. In Proceedings of the 3rd ACM international conference on web search and data mining. New York, New York, USA, pp. 441\u2013450.","DOI":"10.1145\/1718487.1718542"},{"key":"9282_CR41","doi-asserted-by":"crossref","unstructured":"Langlais, P. (2002). Improving a general-purpose statistical translation engine by terminological lexicons. In COMPUTERM 2002: Second International Workshop on Computational Terminology. Taipei, Taiwan, pp. 1\u20137.","DOI":"10.3115\/1118771.1118776"},{"key":"9282_CR42","unstructured":"Mansour, S., Wuebker, J., & Ney, H. (2011). Combining translation and language model scoring for domain-specific data filtering. In International workshop on spoken language translation. San Francisco, California, USA, pp. 222\u2013229."},{"key":"9282_CR43","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MIC.2005.59","volume":"9","author":"F Menczer","year":"2005","unstructured":"Menczer, F. (2005). Mapping the semantics of Web text and links. IEEE Internet Computing, 9, 27\u201336.","journal-title":"IEEE Internet Computing"},{"key":"9282_CR44","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1023\/A:1007653114902","volume":"39","author":"F Menczer","year":"2000","unstructured":"Menczer, F., & Belew, R. K. (2000). Adaptive retrieval agents: Internalizing local contextand scaling up to the web. Machine Learning, 39, 203\u2013242.","journal-title":"Machine Learning"},{"key":"9282_CR45","unstructured":"Moore, R.C., & Lewis, W. (2010). Intelligent selection of language model training data. In Proceedings of the ACL 2010 conference short papers. Uppsala, Sweden, pp. 220\u2013224."},{"key":"9282_CR46","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"DS Munteanu","year":"2005","unstructured":"Munteanu, D. S., & Marcu, D. (2005). Improving machine translation performance by exploiting non-parallel corpora. Computational Linguistics, 31, 477\u2013504.","journal-title":"Computational Linguistics"},{"key":"9282_CR47","doi-asserted-by":"crossref","unstructured":"Nakov, P. (2008). Improving English-Spanish statistical machine translation: experiments in domain adaptation, sentence paraphrasing, tokenization, and recasing. In Proceedings of the third workshop on statistical machine translation. Columbus, Ohio, USA, pp. 147\u2013150.","DOI":"10.3115\/1626394.1626414"},{"key":"9282_CR48","doi-asserted-by":"crossref","unstructured":"Nie, J.Y., Simard, M., Isabelle, P., & Durand, R. (1999). Cross-language information retrieval based on parallel texts and automatic mining of parallel texts from the Web. In Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval, ACM. New York, New York, USA, pp. 74\u201381.","DOI":"10.1145\/312624.312656"},{"key":"9282_CR49","doi-asserted-by":"crossref","unstructured":"Och, F.J. (2003). Minimum error rate training in statistical machine translation. In Proceedings of the 41st annual meeting on association for computational linguisticsal international acm sigir conference on research and development in information retrieval, ACM. Sapporo, Japan, pp. 160\u2013167.","DOI":"10.3115\/1075096.1075117"},{"key":"9282_CR72","unstructured":"Papavassiliou, V., Prokopidis, P., & Thurmair, G. (2013). A modular open-source focused crawler for mining monolingual and bilingual corpora from the web. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora (pp. 43\u201351). Sofia: Association for Computational Linguistics."},{"key":"9282_CR50","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W.J. (2002). BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the association for computational linguistics. Philadelphia, Pennsylvania, USA, pp. 311\u2013318."},{"key":"9282_CR51","unstructured":"Pecina, P., Toral, A., Way, A., Papavassiliou, V., Prokopidis, P., & Giagkou, M. (2011). Towards using web-crawled data for domain adaptation in statistical machine translation. In Proceedings of the 15th annual conference of the European associtation for machine translation. Leuven, Belgium, pp. 297\u2013304."},{"key":"9282_CR53","unstructured":"Pecina, P., Toral, A., Papavassiliou, V., Prokopidis, P., & van Genabith, J. (2012a). Domain adaptation of statistical machine translation using Web-crawled resources: a case study. In M. Cettolo, M. Federico, L. Specia & A. Way (Eds.), Proceedings of the 16th annual conference of the European association for machine translation. Trento, Italy, pp. 145\u2013152."},{"key":"9282_CR52","unstructured":"Pecina, P., Toral, A., & van Genabith, J. (2012b). Simple and effective parameter tuning for domain adaptation of statistical machine translation. In Proceedings of the 24th international conference on computational linguistics. Mumbai, India, pp. 2209\u20132224."},{"key":"9282_CR54","unstructured":"Penkale, S., Haque, R., Dandapat, S., Banerjee, P., Srivastava, A.K., Du, J., et al. (2010). MaTrEx: The DCU MT system for WMT 2010. In Proceedings of the joint fifth workshop on statistical machine translation and MetricsMATR. Uppsala, Sweden, pp. 143\u2013148."},{"key":"9282_CR55","unstructured":"Poch, M., Toral, A., Hamon, O., Quochi, V., & Bel, N. (2012). Towards a user-friendly platform for building language resources based on web services. In N. Calzolari, K. Choukri, T. Declerck, M.U. Dogan, B. Maegaard, J. Mariani, J. Odijk & S. Piperidis (Eds.), LREC, European Language Resources Association (ELRA). pp. 1156\u20131163."},{"key":"9282_CR56","unstructured":"Qi, X., & Davison, B. D. (2009). Web page classification: Features and algorithms. ACM Computing Surveys 41, 12:1\u201312:31."},{"key":"9282_CR57","unstructured":"Qin, J., & Chen, H. (2005). Using genetic algorithm in building domain-specific collections: An experiment in the nanotechnology domain. In Proceedings of the 38th annual Hawaii international conference on system sciences (Vol. 4). Big Island, Hawaii, USA: IEEE Computer Society."},{"key":"9282_CR58","first-page":"349","volume":"29","author":"P Resnik","year":"2003","unstructured":"Resnik, P., & Smith, N. A. (2003). The Web as a parallel corpus. Computational Linguistics, Special Issue on the Web as Corpus, 29, 349\u2013380.","journal-title":"Computational Linguistics, Special Issue on the Web as Corpus"},{"key":"9282_CR59","unstructured":"Sanchis-Trilles, G., & Casacuberta, F. (2010). Log-linear weight optimisation via bayesian adaptation in statistical machine translation. In The 23rd international conference on computational linguistics, posters volume. Beijing, China, pp. 1077\u20131085."},{"key":"9282_CR60","unstructured":"Sennrich, R. (2012). Perplexity minimization for translation model domain adaptation in statistical machine translation. In Proceedings of the 13th conference of the European chapter of the association for computational linguistics. Avignon, France, pp. 539\u2013549."},{"key":"9282_CR61","unstructured":"Snover, M., Dorr, B., Schwartz, R., Micciulla, L., & Makhoul, J. (2006). A study of translation edit rate with targeted human annotation. In Proceedings of the 7th biennial conference of the association for machine translation in the Americas. Cambridge, MA, USA, pp. 223\u2013231."},{"key":"9282_CR62","unstructured":"Spousta, M., Marek, M., & Pecina, P. (2008). Victor: The Web-page cleaning tool. In Proceedings of the 4th web as corpus workshop: Can we beat Google?. Marrakech, Morocco, pp. 12\u201317."},{"key":"9282_CR63","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s10791-005-6993-5","volume":"8","author":"P Srinivasan","year":"2005","unstructured":"Srinivasan, P., Menczer, F., & Pant, G. (2005). A general evaluation framework for topical crawlers. Information Retrieval, 8, 417\u2013447.","journal-title":"Information Retrieval"},{"key":"9282_CR64","doi-asserted-by":"crossref","unstructured":"Stolcke, A. (2002). SRILM-an extensible language modeling toolkit. In Proceedings of international conference on spoken language processing. Denver, Colorado, USA, pp. 257\u2013286.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"9282_CR65","doi-asserted-by":"crossref","unstructured":"Tillmann, C., Vogel, S., Ney, H., Zubiaga, A., & Sawaf, H. (1997). Accelerated dp based search for statistical translation. In Proceedings of the fifth European conference on speech communication and technology. Rhodes, Greece, pp. 2667\u20132670.","DOI":"10.21437\/Eurospeech.1997-673"},{"key":"9282_CR66","unstructured":"Toral, A. (2013). Hybrid selection of language model training data using linguistic information and perplexity. In Proceedings of the second workshop on hybrid approaches to translation. Sofia, Bulgaria, pp. 8\u201312."},{"key":"9282_CR67","unstructured":"Varga, D., N\u00e9meth, L., Hal\u00e1csy, P., Kornai, A., Tr\u00f3n, V., & Nagy, V. (2005). Parallel corpora for medium density languages. In Proceedings of the recent advances in natural language processing. Borovets, Bulgaria, pp. 590\u2013596."},{"key":"9282_CR68","doi-asserted-by":"crossref","unstructured":"Wu, H., & Wang, H. (2004). Improving domain-specific word alignment with a general bilingual corpus. In Proceedings of the 6th conference of the association for machine translation in the Americas. Washington, DC, USA, pp. 262\u2013271.","DOI":"10.1007\/978-3-540-30194-3_29"},{"key":"9282_CR69","doi-asserted-by":"crossref","unstructured":"Wu, H., Wang, H., & Zong, C. (2008). Domain adaptation for statistical machine translation with domain dictionary and monolingual corpora. In Proceedings of the 22nd international conference on computational linguistics. Manchester, United Kingdom, Vol. 1, pp. 993\u20131000.","DOI":"10.3115\/1599081.1599206"},{"issue":"1","key":"9282_CR70","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TKDE.2004.1264823","volume":"16","author":"H Yu","year":"2004","unstructured":"Yu, H., Han, J., & Chang, K. C. C. (2004). PEBL: Web page classification without negative examples. IEEE Transactions on Knowledge and Data Engineering, 16(1), 70\u201381.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"9282_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, K., Gao, J., & Vines, P. (2006). Automatic acquisition of Chinese-English parallel corpus from the Web. In Proceedings of the 28th European conference on information retrieval. London, UK, pp. 420\u2013431.","DOI":"10.1007\/11735106_37"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-014-9282-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-014-9282-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-014-9282-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T11:07:39Z","timestamp":1690715259000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-014-9282-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12,3]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,3]]}},"alternative-id":["9282"],"URL":"https:\/\/doi.org\/10.1007\/s10579-014-9282-3","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12,3]]}}}