{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:45:33Z","timestamp":1742971533887,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319777023"},{"type":"electronic","value":"9783319777030"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-77703-0_37","type":"book-chapter","created":{"date-parts":[[2018,3,24]],"date-time":"2018-03-24T11:53:05Z","timestamp":1521892385000},"page":"358-374","source":"Crossref","is-referenced-by-count":0,"title":["Augmenting SMT with Semantically-Generated Virtual-Parallel Corpora from Monolingual Texts"],"prefix":"10.1007","author":[{"given":"Krzysztof","family":"Wo\u0142k","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Agnieszka","family":"Wo\u0142k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Wo\u0142k, K., Marasek, K., Wo\u0142k, A.: Exploration for Polish-* bi-lingual translation equivalents from comparable and quasi-comparable corpora. In: 2016 Federated Conference on Computer Science and Information Systems (FedCSIS), Gdansk, pp. 517\u2013525 (2016)","DOI":"10.15439\/2016F304"},{"key":"37_CR2","unstructured":"Anderson, S.R., Harrison, D., Horn, L., Zanuttini, R., Lightfoot, D.: How many languages are there in the world?: linguistic society of America (2010). http:\/\/www.linguisticsociety.org\/sites\/default\/files\/how-many-languages.pdf . Accessed 16 Feb 2017"},{"key":"37_CR3","unstructured":"List of languages by number of native speakers (2016). Wikipedia, https:\/\/en.wikipedia.org\/wiki\/List_of_languages_by_number_of_native_speakers . Accessed 16 Feb 2016"},{"key":"37_CR4","unstructured":"Paolillo, J., Anupam, D.: Evaluating language statistics: the Ethnologue and beyond (2006). http:\/\/www.uis.unesco.org\/Library\/Documents\/evaluating-language-statistics-ethnologue-beyond-culture-2006-en.pdf . Accessed 8 Oct 2015"},{"key":"37_CR5","unstructured":"English language in Europe 2016 Wikipedia. https:\/\/en.wikipedia.org\/wiki\/English_language_in_Europe . Accessed 16 Feb 2017"},{"key":"37_CR6","unstructured":"Munteanu, D., Fraser, A., Marcu, D.: Improved machine translation performance via parallel sentence extraction from comparable corpora. In: Human Language Technologies-The 2004 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Marina del Rey, pp. 265\u2013272 (2004)"},{"key":"37_CR7","unstructured":"Callison-Burch, C., Osborne, M.: Co-training for statistical machine translation. Dissertation, School of Informatics, University of Edinburgh (2002)"},{"key":"37_CR8","first-page":"237","volume-title":"Learning Machine Translation","author":"N Ueffing","year":"2009","unstructured":"Ueffing, N., Haffari, G., Sarkar, A.: Semisupervised learning for machine translation. In: Goutte, C., Cancedda, N., Dymetman, M., Foster, G. (eds.) Learning Machine Translation, pp. 237\u2013256. MIT Press, Pittsburgh (2009)"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Mann, G., Yarowsky, D.: Multipath translation lexicon induction via bridge languages. In: Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics on Language Technologies, Pittsburgh, pp. 1\u20138 (2001)","DOI":"10.3115\/1073336.1073356"},{"key":"37_CR10","unstructured":"Kumar, S., Och, F., Macherey, W.: Improving word alignment with bridge languages. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, pp. 42\u201350 (2007)"},{"issue":"3","key":"37_CR11","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10590-008-9041-6","volume":"21","author":"H Wu","year":"2007","unstructured":"Wu, H., Wang, H.: Pivot language approach for phrase-based statistical machine translation. Mach. Transl. 21(3), 165\u2013181 (2007)","journal-title":"Mach. Transl."},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Habash, N., Hu, J.: Improving Arabic-Chinese statistical machine translation using English as pivot language. In: Proceedings of the Fourth Workshop on Statistical Machine Translation. Association of Computational Linguistics, Athens, pp. 173\u2013181 (2009)","DOI":"10.3115\/1626431.1626467"},{"key":"37_CR13","unstructured":"Eisele, A., Federmann, C., Uszkoreit, H., Saint-Amand, H., Kay, M., Jellinghaus, M., Hunsicker, S., Herrmann, T., Chen, Y.: Hybrid machine translation architectures within and beyond the EuroMatrix project. In: Hutchins, J., Hahn, W.V. (eds.) Hybrid MT Methods in Practice: Their Use in Multilingual Extraction, Cross-Language Information Retrieval, Multilingual Summarization, and Applications in Hand-Held Devices. Proceedings of the European Machine Translation Conference, Proceedings of the 12th Annual Conference of the European Association for Machine Translation. HITEC e.V., European Association for Machine Translation, Hamburg, Germany, pp. 27\u201334 (2008)"},{"key":"37_CR14","unstructured":"Cohn, T., Lapata, M.: 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, pp. 728\u2013735 (2007)"},{"key":"37_CR15","unstructured":"Leusch, G., Max, A., Crego, J.M., Ney, H.: Multi-pivot translation by system combination. In: Proceedings of the seventh International Workshop on Spoken Language Translation (IWSLT), Paris, pp. 299\u2013306 (2010)"},{"key":"37_CR16","unstructured":"Bertoldi, N., Barbaiani, M., Federico, M., Cattoni, R.: Phrase-based statistical machine translation with pivot languages. In: Proceedings of IWSLT, Hawaii, pp. 143\u2013149 (2008)"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions. Association of Computational Linguistics, Prague, pp. 177\u2013180 (2007)","DOI":"10.3115\/1557769.1557821"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM-an extensible language modeling toolkit. In: Proceedings of International Conference Spoken Language Processing, Denver, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"37_CR19","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-642-25261-7_30","volume-title":"Security and Intelligent Information Systems: International Joint Conferences, 2011, Warsaw","author":"M Junczys-Dowmunt","year":"2012","unstructured":"Junczys-Dowmunt, M., Szal, A.: SyMGiza\u00a0++: symmetrized word alignment models for statistical machine translation. In: Bouvry, P., K\u0142opotek, M.A., Lepr\u00e9vost, F., Marciniak, M., Mykowiecka, A., Rybi\u0144ski, H. (eds.) Security and Intelligent Information Systems: International Joint Conferences, 2011, Warsaw, pp. 379\u2013390. Springer, Heidelberg (2012)"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Durrani, N., Sajjad, H., Hoang, H., Koehn, P.: Integrating an unsupervised transliteration model into statistical machine translation. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, pp. 148\u2013153 (2014)","DOI":"10.3115\/v1\/E14-4029"},{"key":"37_CR21","unstructured":"Cettolo, M., Girardi, C., Fedirico, M.: WIT3: web inventory of transcribed and translated talks. In: Proceedings of the 16th Conference of the European Association for Machine Translation, Trento, pp. 261\u2013268 (2012)"},{"key":"37_CR22","unstructured":"Abdelali, A., Guzman, F., Sajjad, H., Vogel, S.: The AMARA corpus: building parallel language resources for the educational domain. In: Ninth International Conference on Language Resources and Evaluation (LREC14), Reykjavik, pp. 1044\u20131054 (2014)"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of Association for Computational Linguistics, Philadelphia, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"6","key":"37_CR24","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","volume":"29","author":"L Yujian","year":"2007","unstructured":"Yujian, L., Bo, L.: A normalized Levenshtein distance metric. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1091\u20131095 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Cao, G., Nie, J., Bai, J.: Integrating term relationships into language models. In: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, pp. 298\u2013305 (2005)","DOI":"10.1145\/1076034.1076086"},{"issue":"4","key":"37_CR26","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/csla.1999.0128","volume":"13","author":"S Chen","year":"1999","unstructured":"Chen, S., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13(4), 359\u2013394 (1999)","journal-title":"Comput. Speech Lang."},{"key":"37_CR27","unstructured":"Bellegarda, J.: Data-driven semantic language modeling, Institute for Mathematics and Its Applications Workshop (2000). http:\/\/cmusphinx.sourceforge.net\/wiki\/semanticlanguagemodel . Accessed 16 Feb 2017"},{"key":"37_CR28","unstructured":"Thomo, A.: Latent semantic analysis (LSA) tutorial (2009). http:\/\/webhome.cs.uvic.ca\/~thomo\/svd.pdf . Accessed 16 Feb 2007"},{"key":"37_CR29","unstructured":"Moses statistical machine translation, OOVs (2015). http:\/\/www.statmt.org\/moses\/?n=Advanced.OOVs#ntoc2 . Accessed 27 Sept 2015"},{"key":"37_CR30","unstructured":"Heafield, K.: KenLM: faster and smaller language model queries. In: Proceedings of the Sixth Workshop on Statistical Machine Translation. Association of Computational Linguistics, Edinburgh, pp. 187\u2013197 (2011)"},{"key":"37_CR31","unstructured":"Costa-jussa, M.R., Fonollosa, J.R.: Using linear interpolation and weighted reordering hypotheses in the Moses system. In: Seventh Conference on International Language Resources and Evaluation, Valletta, pp. 1712\u20131718 (2011)"},{"key":"37_CR32","unstructured":"Moses statistical machine translation, Build reordering model (2013) http:\/\/www.statmt.org\/moses\/?n=FactoredTraining.Build . Reordering Model. Accessed 10 Oct 2015"},{"key":"37_CR33","unstructured":"Axelrod, A., He, X., Gao, J.: Domain adaptation via pseudo in-domain data selection. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association of Computational Linguistics, Edinburgh, pp. 355\u2013362 (2011)"},{"key":"37_CR34","first-page":"745485","volume":"2014","author":"L Wang","year":"2014","unstructured":"Wang, L., Wong, D.F., Chao, L.S., Lu, Y., Xing, J.: A systematic comparison of data selection criteria for SMT domain adaptation. Sci. World J. 2014, 745485 (2014)","journal-title":"Sci. World J."},{"key":"37_CR35","unstructured":"Hovy, E.: Toward finely differentiated evaluation metrics for machine translation. In: Proceedings of the EAGLES Workshop on Standards and Evaluation, Pisa, pp. 127\u2013133 (1999)"},{"key":"37_CR36","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/3-540-39965-8_11","volume-title":"Envisioning Machine Translation in the Information Future","author":"Michelle Vanni","year":"2000","unstructured":"Vanni, M., Reeder, F.: How are you doing? A look at MT evaluation. In: White, J.S. (eds.), Envisioning Machine Translation in the Information Future, AMTA 2000. LNCS, vol. 1934. Springer, Heidelberg (2000)"},{"key":"37_CR37","doi-asserted-by":"publisher","first-page":"172","DOI":"10.4236\/ojs.2012.22019","volume":"2","author":"ICA Oyeka","year":"2012","unstructured":"Oyeka, I.C.A., Ebuh, G.U.: Modified Wilcoxon signed-rank test. Open J. Stat. 2, 172\u2013176 (2012)","journal-title":"Open J. Stat."},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Lin, S., Verspoor, K.: A semantics-enhanced language model for unsupervised word sense disambiguation. In: Ninth International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2008). Lecture Notes in Computer Science (LNCS), Haifa, pp. 287\u2013298 (2008)","DOI":"10.1007\/978-3-540-78135-6_24"}],"container-title":["Advances in Intelligent Systems and Computing","Trends and Advances in Information Systems and Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77703-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T22:47:35Z","timestamp":1660690055000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77703-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319777023","9783319777030"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77703-0_37","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2018]]}}}