{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T06:19:42Z","timestamp":1761977982513,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642416439"},{"type":"electronic","value":"9783642416446"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-41644-6_15","type":"book-chapter","created":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T05:31:14Z","timestamp":1380605474000},"page":"151-163","source":"Crossref","is-referenced-by-count":2,"title":["An Efficient Framework to Extract Parallel Units from Comparable Data"],"prefix":"10.1007","author":[{"given":"Lu","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"2","key":"15_CR1","first-page":"263","volume":"19","author":"F. Brown Peter","year":"1993","unstructured":"Brown Peter, F., Della Pietra, S.A., Della Pietra, V.J., Mercer, R.L.: The mathematics of machine translation: Parameter estimation. Computational Linguistics\u00a019(2), 263\u2013311 (1993)","journal-title":"Computational Linguistics"},{"issue":"1","key":"15_CR2","first-page":"61","volume":"19","author":"T. Dunning","year":"1993","unstructured":"Dunning, T.: Accurate methods for the statistics of surprise and coincidence. Computational Linguistics\u00a019(1), 61\u201374 (1993)","journal-title":"Computational Linguistics"},{"key":"15_CR3","unstructured":"Fung, P., Cheung, P.: Mining very non-parallel corpora: Parallel sentence and lexicon extraction vie bootstrapping and EM. In: EMNLP 2004, pp. 57\u201363 (2004a)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Koehn, P., Och, F.J., Marcu, D.: Statistical phrase based translation. In: Proceedings of the Joint Conference on Human Language Technologies and the Annual Meeting of the North American Chapter of the Association of Computational Linguistics, HLT-NAACL (2003)","DOI":"10.3115\/1073445.1073462"},{"key":"15_CR5","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.-C., Dyer, C., Bojar, O.: Moses: Open source toolkit for Statistical Machine Translation. In: Proceedings of the ACL 2007 Demo and Poster Sessions, pp. 177\u2013180 (2007)","DOI":"10.3115\/1557769.1557821"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Moore, R.C.: Improving IBM word alignment model 1. In: ACL 2004, pp. 519\u2013526 (2004a)","DOI":"10.3115\/1218955.1219021"},{"key":"15_CR7","unstructured":"Moore, R.C.: On log-likelihood-ratios and the significance of rare events. In: EMNLP 2004, pp. 333\u2013340 (2004b)"},{"issue":"4","key":"15_CR8","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"D.S. Munteanu","year":"2005","unstructured":"Munteanu, D.S., Marcu, D.: Improving machine translation performance by exploiting non-parallel corpora. Computational Linguistics\u00a031(4), 477\u2013504 (2005)","journal-title":"Computational Linguistics"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Munteanu, D.S., Marcu, D.: Extracting parallel sub-sentential fragments from nonparallel corpora. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, pp. 81\u201388 (2006)","DOI":"10.3115\/1220175.1220186"},{"key":"15_CR10","unstructured":"Och, F.J., Tillmann, C., Ney, H.: Improved alignment models for statistical machine translation. In: Proceedings of the Joint Conference of Empirical Methods in Natural Language Processing and Very Large Corpora, pp. 20\u201328 (1999)"},{"key":"15_CR11","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 ACL, Philadelpha, Pennsylvania, USA, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"15_CR12","unstructured":"Quirk, C., Udupa, R.U., Menezes, A.: Generative models of noisy translations with applications to parallel fragment extraction. In: Proceedings of the Machine Translation Summit XI, Copenhagen, Denmark, pp. 377\u2013384 (2007)"},{"key":"15_CR13","unstructured":"Riesa, J., Marcu, D.: Automatic parallel fragment extraction from noisy data. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 538\u2013542. Association for Computational Linguistics (2012)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM - An Extensible Language Modeling Toolkit. In: Proceedings of ICSLP, vol.\u00a02, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"15_CR15","unstructured":"Smith, J.R., Quirk, C., Toutanova, K.: Extracting parallel sentences from comparable corpora using document level alignment. In: Proceedings of the Human Language Technologies\/North American Association for Computational Linguistics, pp. 403\u2013411 (2010)"},{"key":"15_CR16","unstructured":"Tufi\u015f, D., Ion, R., Ceau\u015fu, A., \u015etef\u0103nescu, D.: Improved Lexical Alignment by Combining Multiple Reified Alignments. In: Proceedings of EACL 2006, Trento, Italy, pp. 153\u2013160 (2006)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Tillmann, C.: A Beam-Search extraction algorithm for comparable data. In: Proceedings of ACL, pp. 225\u2013228 (2009)","DOI":"10.3115\/1667583.1667653"},{"key":"15_CR18","unstructured":"Ture, F., Lin, J.: Why not grab a free lunch? Mining large corpora for parallel sentences to improve translation modeling. In: HLT-NAACL, pp. 626\u2013630 (2012)"},{"key":"15_CR19","unstructured":"Zhao, B., Vogel, S.: Adaptive parallel sentences mining from web bilingual news collection. In: IEEE International Conference on Data Mining, Maebashi City, Japan, pp. 745\u2013748 (2002)"},{"key":"15_CR20","unstructured":"\u015etef\u0103nescu, D., Ion, R., Hunsicker, S.: Hybrid parallel sentence mining from comparable corpora. In: Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT 2012), Trento, Italy (2012)"}],"container-title":["Communications in Computer and Information Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-41644-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T15:04:22Z","timestamp":1746025462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-41644-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642416439","9783642416446"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-41644-6_15","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2013]]}}}