{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:42:19Z","timestamp":1742956939216,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319990033"},{"type":"electronic","value":"9783319990040"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-319-99004-0_1","type":"book-chapter","created":{"date-parts":[[2019,2,6]],"date-time":"2019-02-06T12:11:22Z","timestamp":1549455082000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Introduction"],"prefix":"10.1007","author":[{"given":"Inguna","family":"Skadi\u0146a","sequence":"first","affiliation":[]},{"given":"Robert","family":"Gaizauskas","sequence":"additional","affiliation":[]},{"given":"Andrejs","family":"Vasi\u013cjevs","sequence":"additional","affiliation":[]},{"given":"Monica Lestari","family":"Paramita","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,7]]},"reference":[{"unstructured":"Abdul-Rauf, S., & Schwenk, H. (2009). On the use of comparable corpora to improve SMT performance. EACL 2009: Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (pp. 16\u201323), Athens, Greece.","key":"1_CR1"},{"issue":"4","key":"1_CR2","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10590-011-9114-9","volume":"25","author":"S Abdul-Rauf","year":"2011","unstructured":"Abdul-Rauf, S., & Schwenk, H. (2011). Parallel sentence generation from comparable corpora for improved SMT. Machine Translation, 25(4), 341\u2013375.","journal-title":"Machine Translation"},{"unstructured":"Adafre, S. F., & de Rijke, M. (2006). Finding similar sentences across multiple languages in Wikipedia. Proceedings of the EACL Workshop on New Text, Trento, Italy.","key":"1_CR3"},{"unstructured":"Azpeitia, A., Etchegoyhen, T., & Martinez Garcia, E. (2018). Extracting parallel sentences from comparable corpora with STACC variants. Proceedings of the 11th Workshop on Building and Using Comparable Corpora (pp. 48\u201352).","key":"1_CR5"},{"unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. CoRR, abs\/1409.0. article. Retrieved from \n                  http:\/\/arxiv.org\/abs\/1409.0473","key":"1_CR6"},{"unstructured":"Bojar, O., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huck, M., et al. (2016). Findings of the 2016 conference on machine translation. Proceedings of the First Conference on Machine Translation (WMT 2016), Vol. 2: Shared Task Papers (pp. 131\u2013198).","key":"1_CR7"},{"doi-asserted-by":"crossref","unstructured":"Bojar, O., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huang, S., et al. (2017). Findings of the 2017 conference on machine translation (WMT17). Proceedings of the Second Conference on Machine Translation, Vol. 2: Shared Task Papers (pp. 169\u2013214). Association for Computational Linguistics, Copenhagen, Denmark. Retrieved from \n                  http:\/\/www.aclweb.org\/anthology\/W17-4717","key":"1_CR8","DOI":"10.18653\/v1\/W17-4717"},{"unstructured":"Ceau\u015fu, A., \u015etef\u0103nescu, D., & Tufi\u015f, D. (2006). Acquis communautaire sentence alignment using support vector machines. Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC 2006) (pp. 2134\u20132137).","key":"1_CR10"},{"doi-asserted-by":"crossref","unstructured":"Chiao, Y., & Zweigenbaum, P. (2002). Looking for candidate translational equivalents in specialized, comparable. COLING '02 Proceedings of the 19th International Conference on Computational Linguistics (Vol. 2, pp. 1\u20135).","key":"1_CR11","DOI":"10.3115\/1071884.1071904"},{"unstructured":"Daille, B., & Morin, E. (2008). An effective compositional model for lexical alignment. Proceedings, 3rd International Joint Conference on Natural Language Processing (IJCLNP) (pp. 95\u2013102).","key":"1_CR12"},{"doi-asserted-by":"crossref","unstructured":"Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R. M., & Makhoul, J. (2014). Fast and robust neural network joint models for statistical machine translation. ACL (1) (pp. 1370\u20131380). In Proceedings.","key":"1_CR13","DOI":"10.3115\/v1\/P14-1129"},{"unstructured":"EAGLES. (1996). Preliminary recommendations on corpus typology. Electronic Resource: \n                  http:\/\/www.ilc.cnr.it\/EAGLES96\/corpustyp\/corpustyp.html","key":"1_CR14"},{"unstructured":"Etchegoyhen, T., & Azpeitia, A. (2016). Set-theoretic alignment for comparable corpora. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Vol.1: Long Papers, pp. 2009\u20132018).","key":"1_CR15"},{"unstructured":"Fung, P., & Cheung, P. (2004). Mining very-non-parallel corpora: Parallel sentence and lexicon extraction via bootstrapping and EM. Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-2004) (pp. 57\u201363), Barcelona, Spain.","key":"1_CR16"},{"unstructured":"Hewavitharana, S., & Vogel, S. (2008). Enhancing a statistical machine translation system by using an automatically extracted parallel corpus from comparable sources. Proceedings of the Workshop on Comparable Corpora, LREC\u201908 (pp. 7\u201310).","key":"1_CR17"},{"doi-asserted-by":"crossref","unstructured":"Ion, R., & Tufi\u015f, D. (2007). RACAI: Meaning affinity models. Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007) (pp. 282\u2013287), Association for Computational Linguistics, Prague, Czech Republic, June 2007.","key":"1_CR18","DOI":"10.3115\/1621474.1621535"},{"unstructured":"Irimia, E. (2009). Metode de traducere automat\u0103 prin analogie. Aplica\u0163ii pentru limbile rom\u00e2n\u0103 \u015fi englez\u0103. (Methods for Analogy-based Machine Translation. Applications for Romanian and English). PhD thesis, March 2009.","key":"1_CR19"},{"unstructured":"Irvine, A., & Callison-Burch, Ch. (2013). Combining bilingual and comparable corpora for low resource machine translation. Proceedings of the Eighth Workshop on Statistical Machine Translation (pp. 262\u2014270).","key":"1_CR20"},{"doi-asserted-by":"crossref","unstructured":"Jean, S., Firat, O., Cho, K., Memisevic, R., & Bengio, Y. (2015). Montreal neural machine translation systems for WMT15. Proceedings of the Tenth Workshop on Statistical Machine Translation (pp. 134\u2013140).","key":"1_CR21","DOI":"10.18653\/v1\/W15-3014"},{"issue":"1","key":"1_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1075\/ijcl.6.1.05kil","volume":"6","author":"A Kilgarriff","year":"2001","unstructured":"Kilgarriff, A. (2001). Comparing corpora. International Journal of Corpus Linguistics, 6(1), 1\u201337.","journal-title":"International Journal of Corpus Linguistics"},{"unstructured":"Koehn, P. (2005). Europarl: A parallel corpus for statistical machine translation. Proceedings of Machine Translation Summit X.","key":"1_CR23"},{"unstructured":"Koehn, P. (2010). Statistical machine translation. Cambridge University Press.","key":"1_CR24"},{"doi-asserted-by":"crossref","unstructured":"Koehn, P., & Knowles, R. (2017). Six challenges for neural machine translation. Proceedings of the First Workshop on Neural Machine Translation, NMT@ACL 2017 (pp. 28\u201339), Vancouver, Canada, August 4, 2017.","key":"1_CR26","DOI":"10.18653\/v1\/W17-3204"},{"unstructured":"Li, B., & Gaussier, E. (2010). Improving corpus comparability for bilingual lexicon extraction from comparable corpora. Proceedings of COLING 2010, Beijing, China.","key":"1_CR29"},{"unstructured":"Lu, B., Jiang, T., Chow, K., & Tsou, B. K. (2010). Building a large English-Chinese parallel corpus from comparable patents and its experimental application to SMT. Proceedings of the 3rd Workshop on Building and Using Comparable Corpora: From Parallel to Non-parallel Corpora, Valletta, Malta (pp. 42\u201348).","key":"1_CR30"},{"doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (pp. 1412\u20131421).","key":"1_CR31","DOI":"10.18653\/v1\/D15-1166"},{"key":"1_CR33","doi-asserted-by":"publisher","first-page":"18","DOI":"10.21832\/9781853599873-005","volume-title":"Incorporating Corpora","author":"Tony McEnery","year":"2007","unstructured":"McEnery, A., & Xiao, Z. (2007). Parallel and comparable corpora? Incorporating Corpora: Translation and the Linguist. Translating Europe. Multilingual Matters, Clevedon."},{"unstructured":"Morin, E., Daille, B., Takeuchi, K., & Kageura, K. (2007). Bilingual terminology mining \u2013 Using brain, not brawn comparable corpora. Proceedings, 45th Annual Meeting of the Association for Computational Linguistics (ACL) (pp. 664\u2013671).","key":"1_CR34"},{"issue":"4","key":"1_CR35","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"D Munteanu","year":"2005","unstructured":"Munteanu, D., & Marcu, D. (2005). Improving machine translation performance by exploiting non-parallel corpora. Computational Linguistics, 31(4), 477\u2013504.","journal-title":"Computational Linguistics"},{"unstructured":"Pinnis, M., Ion, R., \u015etef\u0103nescu, D., Su, F., Skadi\u0146a, I., Vasi\u013cjevs, A. et al. (2012). ACCURAT toolkit for multi-level alignment and information extraction from comparable corpora. Proceedings of the ACL 2012 System Demonstrations (pp. 91\u201396). Association for Computational Linguistics, Jeju, South Korea.","key":"1_CR36"},{"doi-asserted-by":"crossref","unstructured":"Rapp, R. (1995). Identifying word translations in non-parallel texts. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (pp. 320\u2013322).","key":"1_CR37","DOI":"10.3115\/981658.981709"},{"doi-asserted-by":"crossref","unstructured":"Rayson, P., & Garside, R. (2000) Comparing corpora using frequency profiling. Proceedings of the Comparing Corpora Workshop at ACL\u201900 (pp. 1\u20136).","key":"1_CR38","DOI":"10.3115\/1604683.1604686"},{"unstructured":"Rehm, G., & Uszkoreit, H. (Eds.). (2012). White paper series. Springer.","key":"1_CR39"},{"doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., & Birch, A. (2016a). Edinburgh neural machine translation systems for WMT 16. Proceedings of the First Conference on Machine Translation, Vol. 2: Shared Task Papers (pp. 368\u2013373), Berlin, Germany.","key":"1_CR41","DOI":"10.18653\/v1\/W16-2323"},{"doi-asserted-by":"crossref","unstructured":"Sennrich, R., Hadow, B., & Birch, A. (2016b). Improving neural machine translation models with monolingual data. Proceedings of Annual Meeting of ACL (pp. 86\u201396).","key":"1_CR42","DOI":"10.18653\/v1\/P16-1009"},{"unstructured":"Sharoff, S. (2007). Classifying Web corpora into domain and genre using automatic feature identification. Proceedings of 3rd Web as Corpus Workshop, Louvain-la-Neuve, Belgium","key":"1_CR43"},{"unstructured":"Skadi\u0146a, I., Aker, A., Mastropavlos, N., Su, F., Tufi\u0219, D., Verlic, M. et al. (2012). Collecting and using comparable corpora for statistical machine translation. Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC\u201912) (pp. 438\u2013445).","key":"1_CR44"},{"unstructured":"Smith, J.R., Quirk, C., & Toutanova, K. (2010). Extracting parallel sentences from comparable corpora using document level alignment. NAACL-HLT 2010 (pp. 403\u2013411).","key":"1_CR45"},{"unstructured":"\u015etef\u0103nescu, D., Ion, R., & Hunsicker, S. (2012). Hybrid parallel sentence mining from comparable corpora. Proceedings of the 16th Annual Conference of the European Association for Machine Translation (EAMT 2012) (pp. 137\u2013144), Trento, Italy.","key":"1_CR46"},{"unstructured":"Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufi\u015f, D. et al. (2006). The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages. Proceedings of the 5th International Conference on Language Resources and Evaluation: LREC\u201906.","key":"1_CR47"},{"unstructured":"Steinberger, R., Eisele, A., Klocek, S., Pilos, S., & Schl\u00fcter, P. (2012). DGT-TM: A freely available translation memory in 22 languages. Proceedings of LREC\u20192012 (pp. 454\u2013459), Istanbul, Turkey.","key":"1_CR48"},{"unstructured":"Tiedemann, J. (2016). OPUS \u2013 Parallel corpora for everyone. Baltic Journal of Modern Computing (BJMC), 4(2). Special Issue: Proceedings of the 19th Annual Conference of the European Association of Machine Translation (EAMT), 2016.","key":"1_CR50"},{"unstructured":"Tyers, F. M., & Alpren, M. S. (2010). South-East European Times: A parallel corpus of Balkan languages. Proceedings of Workshop \u201cExploitation of Multilingual Resources and Tools for Central and (South) Eastern European Languages\u201d.","key":"1_CR51"},{"doi-asserted-by":"crossref","unstructured":"Utiyama, M., & Isahara, H. (2003). Reliable measures for aligning Japanese-English news articles and sentences. Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (pp. 7\u201312).","key":"1_CR52","DOI":"10.3115\/1075096.1075106"},{"unstructured":"Xu, J., Kennington, C., Przywara, C., & Wanzare, L. (2012). Comparable corpora in Wikipedia text for machine translation. Proceedings of the 6th NIC Symposium 2012: 25 Years HLRZ\/NIC (Book Section). ISBN: 9783893367580, J\u00fclich, Germany, February 2012.","key":"1_CR53"},{"unstructured":"Zhao, B., & Vogel, S. (2002). Adaptive parallel sentences mining from web bilingual news collection. Proceedings of the 2002 I.E. International Conference on Data Mining (ICDM\u201902) (p. 74).","key":"1_CR54"},{"unstructured":"Zweigenbaum, P., Sharoff, S., & Rapp, R. (2018). Overview of the third BUCC shared task: Spotting parallel sentences in comparable corpora. Proceedings of 11th Workshop on Building and Using Comparable Corpora (pp. 39\u201342).","key":"1_CR55"}],"container-title":["Theory and Applications of Natural Language Processing","Using Comparable Corpora for Under-Resourced Areas of Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99004-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T04:24:55Z","timestamp":1558412695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99004-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783319990033","9783319990040"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99004-0_1","relation":{},"ISSN":["2192-032X","2192-0338"],"issn-type":[{"type":"print","value":"2192-032X"},{"type":"electronic","value":"2192-0338"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"7 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}