{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:07:49Z","timestamp":1743152869068,"version":"3.40.3"},"publisher-location":"Cham","reference-count":58,"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_79","type":"book-chapter","created":{"date-parts":[[2018,3,24]],"date-time":"2018-03-24T11:53:05Z","timestamp":1521892385000},"page":"797-812","source":"Crossref","is-referenced-by-count":0,"title":["Statistical Approach to Noisy-Parallel and Comparable Corpora Filtering for the Extraction of Bi-lingual Equivalent Data at Sentence-Level"],"prefix":"10.1007","author":[{"given":"Krzysztof","family":"Wo\u0142k","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emilia","family":"Zawadzka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Agnieszka","family":"Wo\u0142k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"79_CR1","unstructured":"Wu, H., Wang, H.: Comparative study of word alignment heuristics and phrase-based SMT. In: Presented in the 11th Machine Translation Summit \u2013 Second CFP, Copenhagen Business School, Copenhagen, September 2007"},{"issue":"3","key":"79_CR2","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1017\/S1351324906004293","volume":"13","author":"Y Deng","year":"2007","unstructured":"Deng, Y., Shankar, K., William, B.: Segmentation and alignment of parallel text for statistical machine translation. Nat. Lang. Eng. 13(3), 235\u2013260 (2007)","journal-title":"Nat. Lang. Eng."},{"key":"79_CR3","unstructured":"Braune, F., Fraser, A.: Improved unsupervised sentence alignment for symmetrical and asymmetrical parallel corpora. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pp. 81\u201389. Association for Computational Linguistics, Stroudsburg (2010)"},{"key":"79_CR4","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-319-05951-8_11","volume-title":"New Perspectives in Information Systems and Technologies","author":"K Wo\u0142k","year":"2014","unstructured":"Wo\u0142k, K., Marasek, K.: Real-time statistical speech translation. In: Rocha, A., Correia, A.M., Tan, F.B., Stroetmann, K.A. (eds.) New Perspectives in Information Systems and Technologies, vol. 1, pp. 107\u2013113. Springer, Heidelberg (2014)"},{"key":"79_CR5","unstructured":"Cettolo, M., Girardi, C., Federico, M.: WIT3: web inventory of transcribed and translated talks. In Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), pp. 261\u2013268. Fondazione Bruno Kessler (FBK), Trento (2012)"},{"key":"79_CR6","first-page":"117","volume":"2011","author":"A Santos","year":"2011","unstructured":"Santos, A.: A survey on parallel corpora alignment. MI-STAR 2011, 117\u2013128 (2011)","journal-title":"MI-STAR"},{"key":"79_CR7","doi-asserted-by":"crossref","unstructured":"Brown, P.F., Lai, J.C., Mercer, R.L.: Aligning sentences in parallel corpora. In: Proceedings of the 29th Annual Meeting on Association for Computational Linguistics, pp. 169\u2013176. Association for Computational Linguistics, Stroudsburg (1991)","DOI":"10.3115\/981344.981366"},{"key":"79_CR8","doi-asserted-by":"crossref","unstructured":"Gale, W.A., Church, K.W.: Identifying word correspondences in parallel texts. In: Proceedings of the workshop on Speech and Natural Language, HLT 1991, pp. 152\u2013157. Association for Computational Linguistics, Stroudsburg (1991)","DOI":"10.3115\/112405.112428"},{"issue":"292","key":"79_CR9","first-page":"247","volume":"4","author":"D Varga","year":"2007","unstructured":"Varga, D., Hal\u00e1csy, P., Kornai, A., Nagy, V., N\u00e9meth, L., Tr\u00f3n, V.: Parallel corpora for medium density languages. Amsterdam Stud. Theor. Hist. Linguist. Sci. Ser. 4(292), 247 (2007)","journal-title":"Amsterdam Stud. Theor. Hist. Linguist. Sci. Ser."},{"key":"79_CR10","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-319-05951-8_22","volume-title":"New Perspectives in Information Systems and Technologies","author":"K Wo\u0142k","year":"2014","unstructured":"Wo\u0142k, K., Marasek, K.: A sentence meaning based alignment method for parallel text corpora preparation. In: Rocha, A., Correia, A.M., Tan, F.B., Stroetmann, K.A. (eds.) New Perspectives in Information Systems and Technologies, vol. 1, pp. 229\u2013237. Springer, Heidelberg (2014)"},{"key":"79_CR11","unstructured":"Marasek, K.: TED Polish-to-English translation system for the IWSLT 2012. Paper Presented in the International Workshop on Spoken Language Translation 2012, Hong Kong, December 2012"},{"key":"79_CR12","unstructured":"Tiedemann, J. Parallel data, tools and interfaces in OPUS. In: The Eighth International Conference on Language Resources and Evaluation (LREC), pp. 2214\u20132218. European Language Resources Association, Istanbul (2012)"},{"key":"79_CR13","unstructured":"Lison, P., Tiedemann, J.: OpenSubtitles2016: extracting large parallel corpora from movie and TV subtitles (2016). http:\/\/www.lrecconf.org\/proceedings\/lrec2016\/pdf\/947_Paper.pdf . Accessed Dec 2016"},{"key":"79_CR14","unstructured":"Wo\u0142k, K., Marasek, K.: Polish-English speech statistical machine translation systems for the IWSLT 2013. In: Proceedings of the 10th International Workshop on Spoken Language Translation, pp. 113\u2013119. Springer, Heidelberg (2013)"},{"key":"79_CR15","first-page":"157","volume-title":"Polish-Language Parallel Corpora","author":"K Wo\u0142k","year":"2016","unstructured":"Wo\u0142k, K., Rejmund, E., Marasek, K.: Multi-domain machine translation enhancements by parallel data extraction from comparable corpora. In: Ewa, G., Agnieszka, L.S. (eds.) Polish-Language Parallel Corpora, pp. 157\u2013179. Instytut Lingwistyki Stosowanej, Warszawa (2016)"},{"key":"79_CR16","unstructured":"Berrotar\u00e1n, G.G., Carrascosa, R., Vine, A.: Yalign documentation (2015). http:\/\/yalign.readthedocs.org\/en\/latest\/ . Accessed Dec 2016"},{"key":"79_CR17","unstructured":"Musso, G.: Sequence alignment (Needleman-Wunsch, Smith-Waterman). CSC2427: Algorithms in Molecular Biology (2006). http:\/\/www.cs.utoronto.ca\/~brudno\/bcb410\/lec2notes.pdf . Accessed Dec 2016"},{"key":"79_CR18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/978-3-319-24033-6_4","volume-title":"Text, Speech, and Dialogue","author":"K Wo\u0142k","year":"2015","unstructured":"Wo\u0142k, K., Marasek, K.: Tuned and GPU-accelerated parallel data mining from comparable corpora. In: Kr\u00e1l, P., Matou\u0161ek, V. (eds.) Text, Speech, and Dialogue, pp. 32\u201340. Springer, Heidelberg (2015)"},{"key":"79_CR19","unstructured":"Tyers, F.M., Pienaar, J.A.: Extracting bilingual word pairs from Wikipedia. In: Collaboration: Interoperability Between People in the Creation of Language Resources for Less-Resourced Languages, vol. 19, pp. 19\u201322 (2008)"},{"key":"79_CR20","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, pp. 177\u2013180. Association for Computational Linguistics, Stroudsburg","DOI":"10.3115\/1557769.1557821"},{"issue":"1","key":"79_CR21","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1162\/089120103321337421","volume":"29","author":"FJ Och","year":"2003","unstructured":"Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Comput. Linguist. 29(1), 19\u201351 (2003)","journal-title":"Comput. Linguist."},{"key":"79_CR22","unstructured":"Vuli\u0107, I.: Term alignment: state of the art overview (2010). http:\/\/people.cs.kuleuven.be\/~ivan.vulic\/Files\/TASOA.pdf . Accessed Dec 2016"},{"key":"79_CR23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815829","volume-title":"Statistical Machine Translation","author":"P Koehn","year":"2009","unstructured":"Koehn, P.: Statistical Machine Translation. Cambridge University Press, Cambridge (2009)"},{"key":"79_CR24","unstructured":"Collins, M.: Statistical machine translation: IBM models 1 and 2 (2011). http:\/\/www.cs.columbia.edu\/~mcollins\/courses\/nlp2011\/notes\/ibm12.pdf . Accessed Dec 2016"},{"key":"79_CR25","unstructured":"Schoenemann, T.: Computing optimal alignments for the IBM-3 translation model. In: Proceedings of the Fourteenth Conference on Computational Natural Language Learning, pp. 98\u2013106. Association for Computational Linguistics, Stroudsburg (2010)"},{"key":"79_CR26","volume-title":"Improving Word-to-word Alignments Using Morphological Information (Unpublished doctoral dissertation)","author":"PM Fern\u00e1ndez","year":"2008","unstructured":"Fern\u00e1ndez, P.M.: Improving Word-to-word Alignments Using Morphological Information (Unpublished doctoral dissertation). San Diego State University, California (2008)"},{"issue":"2","key":"79_CR27","first-page":"263","volume":"19","author":"PF Brown","year":"1993","unstructured":"Brown, P.F., Pietra, V.J.D., Pietra, S.A.D., Mercer, R.L.: The mathematics of statistical machine translation: parameter estimation. Comput. Linguist. 19(2), 263\u2013311 (1993)","journal-title":"Comput. Linguist."},{"key":"79_CR28","unstructured":"Bojar, O., Rosa, R., Tamchyna, A.: Chimera\u2013three heads for English-to-Czech translation. In: Proceedings of the Eighth Workshop on Statistical Machine Translation, pp. 90\u201396. Association for Computational Linguistics, Stroudsburg (2013)"},{"key":"79_CR29","doi-asserted-by":"crossref","unstructured":"Fujita, A., Isabelle, P.: Expanding paraphrase lexicons by exploiting lexical variants. Paper Presented at the Proceedings of Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL-HLT, Denver, Colorado, USA, June 2015","DOI":"10.3115\/v1\/N15-1065"},{"key":"79_CR30","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M., Sza\u0142, A.: SyMGiza++: a tool for parallel computation of symmetrized word alignment models. In: Computer Science and Information Technology (IMCSIT), Proceedings of the International MultiConference of Engineers and Computer Scientists, pp. 397\u2013401. IEEE, Wis\u0142a (2010)","DOI":"10.1109\/IMCSIT.2010.5679866"},{"key":"79_CR31","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, pp. 355\u2013362. Association for Computational Linguistics, Stroudsburg (2011)"},{"key":"79_CR32","unstructured":"L\u00fc, Y., Huang, J., Liu, Q.: Improving statistical machine translation performance by training data selection and optimization. Paper Presented in the Conference on Empirical Methods in Natural Language Processing - Conference on Computational Natural Language Learning, Prague, Czech Republic, June 2007"},{"key":"79_CR33","unstructured":"Hildebrand, A.S., Eck, M., Vogel, S., Waibel, A.: Adaptation of the translation model for statistical machine translation based on information retrieval. In: Proceedings of EAMT 10th Annual Conference, 30\u201331 May 2005, Budapest, Hungary, pp. 133\u2013142. Association for Computational Linguistics, Stroudsburg (2005)"},{"key":"79_CR34","first-page":"115","volume-title":"Conference of the Association for Machine Translation in the Americas","author":"P Koehn","year":"2004","unstructured":"Koehn, P.: Pharaoh: a beam search decoder for phrase-based statistical machine translation models. In: Frederking, R.E., Taylor, K.B. (eds.) Conference of the Association for Machine Translation in the Americas, pp. 115\u2013124. Springer, Heidelberg (2004)"},{"key":"79_CR35","unstructured":"Daum\u00e9 III, H., Jagarlamudi, J.: Domain adaptation for machine translation by mining unseen words. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers-Vol. 2, pp. 407\u2013412. Association for Computational Linguistics, Stroudsburg (2011)"},{"key":"79_CR36","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 on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Stroudsburg (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"79_CR37","unstructured":"Mansour, S., Ney, H.: A simple and effective weighted phrase extraction for machine translation adaptation. Paper Presented in the International Workshop on Spoken Language Translation 2012, Hong Kong, December 2012"},{"key":"79_CR38","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM-an extensible language modeling toolkit. Paper Presented in the 7th International Conference on Spoken Language Processing, ICSLP2002 - INTERSPEECH 2002, Denver, Colorado, USA, September 2002","DOI":"10.21437\/ICSLP.2002-303"},{"key":"79_CR39","doi-asserted-by":"crossref","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. In Proceedings of the 34th Annual Meeting on Association for Computational Linguistics, pp. 310\u2013318. Association for Computational Linguistics, Stroudsburg (1996)","DOI":"10.3115\/981863.981904"},{"key":"79_CR40","unstructured":"Hovy, E.: Toward finely differentiated evaluation metrics for machine translation. Paper Presented in the Proceedings of the EAGLES Workshop on Standards and Evaluation, Pisa, January 1999"},{"key":"79_CR41","unstructured":"Reeder, F.: Additional mt-eval references. Technical report, International Standards for Language Engineering, Evaluation Working Group (2001)"},{"key":"79_CR42","unstructured":"Lavie, A.: Evaluating the output of machine translation systems (2010). https:\/\/amta2010.amtaweb.org\/AMTA\/papers\/6-04-LavieMTEvaluation.pdf . Accessed Dec 2016"},{"key":"79_CR43","doi-asserted-by":"crossref","unstructured":"Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics. In: Proceedings of the Second International Conference on Human Language Technology Research, pp. 138\u2013145. Morgan Kaufmann Publishers Inc., San Diego (2002)","DOI":"10.3115\/1289189.1289273"},{"key":"79_CR44","unstructured":"Oliver, J.: Global autonomous language exploitation (GALE). DARPA\/IPTO Proposer Information Pamphlet (2005)"},{"key":"79_CR45","unstructured":"Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of association for machine translation in the Americas, pp. 223\u2013231. Association for Machine Translation in the Americas, Stroudsburg (2006)"},{"key":"79_CR46","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372. Association for Computational Linguistics, Stroudsburg (2005)"},{"issue":"2","key":"79_CR47","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(2), 172\u2013176 (2012)","journal-title":"Open J. Stat."},{"key":"79_CR48","doi-asserted-by":"crossref","unstructured":"Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, vol. 1, pp. 48\u201354. Association for Computational Linguistics, Stroudsburg (2003)","DOI":"10.21236\/ADA461156"},{"key":"79_CR49","unstructured":"Shen, L., Sarkar, A., Och, F.J.: Discriminative reranking for machine translation. Paper Presented in the Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004, pp. 177\u2013184. Association for Computational Linguistics, Stroudsburg (2004)"},{"key":"79_CR50","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2478\/v10108-010-0023-5","volume":"94","author":"P Koehn","year":"2010","unstructured":"Koehn, P.: An experimental management system. Prague Bull. Math. Linguist. 94, 87\u201396 (2010)","journal-title":"Prague Bull. Math. Linguist."},{"key":"79_CR51","doi-asserted-by":"crossref","unstructured":"Quirk, C., Menezes, A.: Do we need phrases?: challenging the conventional wisdom in statistical machine translation. In: Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, pp. 9\u201316. Association for Computational Linguistics, Stroudsburg (2006)","DOI":"10.3115\/1220835.1220837"},{"issue":"4","key":"79_CR52","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1162\/coli.2006.32.4.527","volume":"32","author":"JB Marino","year":"2006","unstructured":"Marino, J.B., Banchs, R.E., Crego, J.M., de Gispert, A., Lambert, P., Fonollosa, J.A., Costa-Juss\u00e0, M.R.: N-gram-based machine translation. Comput. Linguist. 32(4), 527\u2013549 (2006)","journal-title":"Comput. Linguist."},{"key":"79_CR53","doi-asserted-by":"crossref","unstructured":"Costa-Juss\u00e0, M.R., Crego, J.M., Vilar, D., Fonollosa, J.A., Mari\u00f1o, J.B., Ney, H.: Analysis and system combination of phrase-and n-gram-based statistical machine translation systems. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume, Short Papers, pp. 137\u2013140. Association for Computational Linguistics, Stroudsburg (2007)","DOI":"10.3115\/1614108.1614143"},{"key":"79_CR54","unstructured":"Johnson, J.H., Martin, J., Foster, G., Kuhn, R.: Improving translation quality by discarding most of the phrasetable. In: Proceedings of Conference on Empirical Methods in Natural Language Processing - Conference on Computational Natural Language Learning (EMNLP-CoNLL 2007), 28\u201330 June 2007, Prague, Czech Republic, pp. 967\u2013975. Association for Computational Linguistics, Stroudsburg (2007)"},{"key":"79_CR55","unstructured":"Kutsumi, T., Yoshimi, T., Kotani, K., Sata, I., Isahara, H.: Selection of entries for a bilingual dictionary from aligned translation equivalents using support vector machines. In: Proceedings of Pacific Association for Computational Linguistics, pp. 24\u201327. Association for Computational Linguistics, Stroudsburg (2005)"},{"key":"79_CR56","unstructured":"Eck, M., Vogel, S., Waibel, A.: Estimating phrase pair relevance for translation model pruning. Paper Presented at the MT Summit XI, The 11th Machine Translation Summit, Copenhagen Business School, Copenhagen, Denmark, September 2007"},{"key":"79_CR57","doi-asserted-by":"crossref","unstructured":"Eck, M., Vogel, S., Waibel, A.: Translation model pruning via usage statistics for statistical machine translation. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pp. 21\u201324. Association for Computational Linguistics, Stroudsburg (2007)","DOI":"10.3115\/1614108.1614114"},{"key":"79_CR58","doi-asserted-by":"crossref","unstructured":"Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R.M., Makhoul, J.: Fast and robust neural network joint models for statistical machine translation. In: The 52nd Annual Meeting of the Association for Computational Linguistics, pp. 1370\u20131380. Association for Computational Linguistics, Stroudsburg (2014)","DOI":"10.3115\/v1\/P14-1129"}],"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_79","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T22:48:46Z","timestamp":1660690126000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77703-0_79"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319777023","9783319777030"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77703-0_79","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2018]]}}}