{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T12:01:05Z","timestamp":1725883265246},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319565347"},{"type":"electronic","value":"9783319565354"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-56535-4_32","type":"book-chapter","created":{"date-parts":[[2017,3,27]],"date-time":"2017-03-27T21:34:36Z","timestamp":1490650476000},"page":"317-327","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Parallel Data Mining After Bilingual Document Alignment"],"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","published-online":{"date-parts":[[2017,3,28]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Wo\u0142k, K., Marasek, K.: Real-Time Statistical Speech Translation. New Perspectives in Information Systems and Technologies, vol. 1, pp. 107\u2013113. Springer, Switzerland (2014)","DOI":"10.1007\/978-3-319-05951-8_11"},{"key":"32_CR2","unstructured":"Wo\u0142k, K., Marasek, K.: Polish\u2013English speech statistical machine translation systems for the IWSLT 2013. In: Proceedings of the 10th International Workshop on Spoken Language Translation, Heidelberg, Germany, pp. 113\u2013119 (2013)"},{"key":"32_CR3","doi-asserted-by":"crossref","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":"32_CR4","unstructured":"Garc\u00eda Berrotar\u00e1n, G., Carrascosa, R., Vine, A.: Yalign documentation. https:\/\/yalign.readthedocs.org . Accessed 01\/2015"},{"key":"32_CR5","unstructured":"Dieny, R., Thevenon, J., Martinez-del-Rincon, J., Nebel, J.-C.: Bioinformatics inspired algorithm for stereo correspondence. In: International Conference on Computer Vision Theory and Applications, Algarve, Portugal, Vilamoura (2011)"},{"key":"32_CR6","unstructured":"Musso, G.: Sequence alignment (Needleman-Wunsch, Smith-Waterman) (2007). http:\/\/www.cs.utoronto.ca\/~brudno\/bcb410\/lec2notes.pdf"},{"key":"32_CR7","unstructured":"Cetollo, 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 (2012)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Mohammadi, M., GasemAghaee, N.: Building bilingual parallel corpora based on Wikipedia. In: 2010 Second International Conference on Computer Engineering and Applications (ICCEA), pp. 264\u2013268. IEEE (2010)","DOI":"10.1109\/ICCEA.2010.203"},{"key":"32_CR9","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":"32_CR10","unstructured":"Yasuda, K., Sumita, E.: Method for building sentence-aligned corpus from Wikipedia. In: AAAI Workshop on Wikipedia and Artificial Intelligence (WikiAI 2008), pp. 263\u2013268 (2008)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Pal, S., Pakray, P., Naskar, S.K.: Automatic building and using parallel resources for SMT from comparable corpora. In: Proceedings of the 3rd Workshop on Hybrid Approaches to Translation (HyTra)@ EACL, pp. 48\u201357 (2014)","DOI":"10.3115\/v1\/W14-1009"},{"key":"32_CR12","unstructured":"Plamada, M., Volk, M.: Mining for domain-specific parallel text from wikipedia. In: Proceedings of the Sixth Workshop on Building and Using Comparable Corpora, ACL 2013, pp. 112\u2013120 (2013)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Str\u00f6tgen, J., Gertz, M., Junghans, C.: An event-centric model for multilingual document similarity. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 953\u2013962 (2011)","DOI":"10.1145\/2009916.2010043"},{"key":"32_CR14","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-642-20128-8_5","volume-title":"Building and Using Comparable Corpora","author":"ML Paramita","year":"2013","unstructured":"Paramita, M.L., Guthrie, D., Kanoulas, E., Gaizauskas, R., Clough, P., Sanderson, M.: Methods for collection and evaluation of comparable documents. In: Sharoff, S., Rapp, R., Zweigenbaum, P., Fung, P. (eds.) Building and Using Comparable Corpora, pp. 93\u2013112. Springer, Heidelberg (2013). doi: 10.1007\/978-3-642-20128-8_5"},{"key":"32_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/11562214_23","volume-title":"Natural Language Processing \u2013 IJCNLP 2005","author":"D Wu","year":"2005","unstructured":"Wu, D., Fung, P.: Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora. In: Dale, R., Wong, K.-F., Su, J., Kwong, O.Y. (eds.) IJCNLP 2005. LNCS (LNAI), vol. 3651, pp. 257\u2013268. Springer, Heidelberg (2005). doi: 10.1007\/11562214_23"},{"key":"32_CR16","unstructured":"Clark, J.H., et al.: Better hypothesis testing for statistical machine translation: Controlling for optimizer instability. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers, vol. 2, pp. 176\u2013181. Association for Computational Linguistics (2011)"},{"key":"32_CR17","series-title":"Advances in Intelligent Systems and Computing","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, Volume 1","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, \u00c1., Correia, A.M., Tan, F.B., Stroetmann, K.A. (eds.) New Perspectives in Information Systems and Technologies, Volume 1. AISC, vol. 275, pp. 229\u2013237. Springer, Cham (2014). doi: 10.1007\/978-3-319-05951-8_22"},{"key":"32_CR18","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 (2011)"},{"key":"32_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","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.) TSD 2015. LNCS (LNAI), vol. 9302, pp. 32\u201340. Springer, Cham (2015). doi: 10.1007\/978-3-319-24033-6_4"},{"key":"32_CR20","unstructured":"Khaladkar, C.S.: An Efficient Implementation of Needleman-Wunsch Algorithm on Graphical Processing Units. P.h.D. thesis, School of Computer Science and Software Engineering, The University of Western Australia (2009)"},{"key":"32_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-642-25261-7_30","volume-title":"Security and Intelligent Information Systems","author":"M Junczys-Dowmunt","year":"2012","unstructured":"Junczys-Dowmunt, M., Sza\u0142, A.: SyMGiza++: 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.) SIIS 2011. LNCS, vol. 7053, pp. 379\u2013390. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-25261-7_30"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Durrani, N., et al.: Integrating an unsupervised transliteration model into statistical machine translation. In: EACL, pp. 148\u2013153 (2014)","DOI":"10.3115\/v1\/E14-4029"},{"key":"32_CR23","unstructured":"Heafield, K.: KenLM: Faster and smaller language model queries. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 187\u2013197. Association for Computational Linguistics (2011)"}],"container-title":["Advances in Intelligent Systems and Computing","Recent Advances in Information Systems and Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-56535-4_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T07:04:14Z","timestamp":1568963054000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-56535-4_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319565347","9783319565354"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-56535-4_32","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2017]]}}}