{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:46:53Z","timestamp":1743040013831,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"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_7","type":"book-chapter","created":{"date-parts":[[2019,2,6]],"date-time":"2019-02-06T12:11:22Z","timestamp":1549455082000},"page":"255-290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["New Areas of Application of Comparable Corpora"],"prefix":"10.1007","author":[{"given":"Reinhard","family":"Rapp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Zock","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serge","family":"Sharoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Forsyth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Babych","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshiaki","family":"Nakazawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadao","family":"Kurohashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,7]]},"reference":[{"issue":"4","key":"7_CR1","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"},{"key":"7_CR2","unstructured":"Adafre, S. F., & de Rijke, M. (2006). Finding similar sentences across multiple languages in Wikipedia. In Proceedings of EACL (pp. 62\u201369)."},{"key":"7_CR3","unstructured":"Armstrong, S., Kempen, M., McKelvie, D., Petitpierre, D., Rapp, R., & Thompson, H. (1998). Multilingual corpora for cooperation. In Proceedings of the 1st International Conference on Linguistic Resources and Evaluation (LREC) (Vol. 2, pp. 975\u2013980), Granada."},{"key":"7_CR4","unstructured":"Brants, T. (2000). TnT \u2212 A statistical part-of-speech tagger. In Proceedings of the 6th Applied Natural Language Processing Conference (pp. 224\u2013231)."},{"key":"7_CR6","unstructured":"Chiao, Y.-C., Sta, J.-D., & Zweigenbaum, P. (2004). A novel approach to improve word translations extraction from non-parallel, comparable corpora. In Proceedings of the International Joint Conference on Natural Language Processing, Hainan, China, AFNLP, 2004."},{"key":"7_CR7","unstructured":"Chu, C., Nakazawa, T., & Kurohashi, S. (2011). Japanese-Chinese phrase alignment using common Chinese characters information. In Proceedings of MT Summit XIII (pp. 475\u2013482), Xiamen, China, September."},{"key":"7_CR8","unstructured":"Chu, C., Nakazawa, T., Kawahara, D., & Kurohashi, S. (2012a, May). Exploiting shared Chinese characters in Chinese word segmentation optimization for Chinese-Japanese machine translation. In Proceedings of the 16th Annual Conference of the European Association for Machine Translation (EAMT2012) (pp. 35\u201342), Trento, Italy."},{"key":"7_CR9","unstructured":"Chu, C., Nakazawa, T., Kawahara, D., & Kurohashi, S. (2012b, May). Chinese characters mapping table of Japanese, Traditional Chinese and Simplified Chinese. In Proceedings of the Eighth Conference on International Language Resources and Evaluation (LREC2012) (pp. 2149\u20132152), Istanbul, Turkey."},{"key":"7_CR10","unstructured":"Chu, C., Nakazawa, T., Kawahara, D., & Kurohashi, S. (2013, August). Chinese\u2013Japanese parallel sentence extraction from quasi\u2013comparable corpora. In Proceedings of the Sixth Workshop on Building and Using Comparable Corpora (pp. 34\u201342). Association for Computational Linguistics, Sofia, Bulgaria."},{"issue":"1","key":"7_CR11","first-page":"61","volume":"19","author":"T Dunning","year":"1993","unstructured":"Dunning, T. (1993). Accurate methods for the statistics of surprise and coincidence. Computational Linguistics, 19(1), 61\u201374.","journal-title":"Computational Linguistics"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Fung, P., & Cheung, P. (2004). Multi-level bootstrapping for extracting parallel sentences from a quasi-comparable corpus. In Proceedings of Coling 2004 (pp. 1051\u20131057), Geneva, Switzerland, Aug 23\u2013Aug 27. COLING.","DOI":"10.3115\/1220355.1220506"},{"key":"7_CR13","unstructured":"Fung, P., & McKeown, K. (1997). Finding terminology translations from non-parallel corpora. In Proceedings of the 5th Annual Workshop on Very Large Corpora (pp. 192\u2013202), Hong Kong."},{"key":"7_CR14","unstructured":"Fung, P., & Yee, L. Y. (1998). An IR approach for translating new words from nonparallel, comparable texts. In Proceedings of COLING-ACL 1998 (Vol. 1, pp. 414\u2013420), Montreal."},{"key":"7_CR15","first-page":"670","volume-title":"Lecture Notes in Computer Science","author":"Chooi-Ling Goh","year":"2005","unstructured":"Goh, C. L., Asahara, M., & Matsumoto, Y. (2005). Building a Japanese-Chinese dictionary using kanji\/hanzi conversion. In Proceedings of the International Joint Conference on Natural Language Processing (pp. 670\u2013681)."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Jongejan, B., & Dalianis, H. (2009). Automatic training of lemmatization rules that handle morphological changes in pre-, in- and suffixes alike. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (pp. 145\u2013153).","DOI":"10.3115\/1687878.1687900"},{"key":"7_CR17","unstructured":"Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In D. Lin, & D. Wu (Eds.), Proceedings of EMNLP 2004 (pp. 388\u2013395). Association for Computational Linguistics, Barcelona, Spain."},{"key":"7_CR18","unstructured":"Koehn, P. (2005). Europarl: A parallel corpus for statistical machine translation. In Proceedings of MT Summit (pp. 79\u201386), Phuket, Thailand."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Koehn, P., Hoang, H., Birch, A., et al. (2007, June). Moses: Open source toolkit for statistical machine translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions (pp. 177\u2013180), Association for Computational Linguistics, Prague, Czech Republic.","DOI":"10.3115\/1557769.1557821"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Kondrak, G., Marcu, D., & Knight, K. (2003). Cognates can improve statistical translation models. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (pp. 46\u201348).","DOI":"10.3115\/1073483.1073499"},{"key":"7_CR21","unstructured":"Kurohashi, S., Nakamura, T., Matsumoto, Y., & Nagao, M. (1994). Improvements of Japanese morphological analyzer JUMAN. In Proceedings of the International Workshop on Sharable Natural Language(pp. 22\u201328)."},{"key":"7_CR22","unstructured":"Laws, F., Michelbacher, L., Dorow, B., Scheible, C., Heid, U., & Sch\u00fctze, H. (2010). A linguistically grounded graph model for bilingual lexicon extraction. In Proceedings of Coling, Poster Volume (pp. 614\u2013622)."},{"issue":"4","key":"7_CR25","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"DS Munteanu","year":"2005","unstructured":"Munteanu, D. S., & Marcu, D. (2005). Improving machine translation performance by exploiting non-parallel corpora. Computational Linguistics, 31(4), 477\u2013504.","journal-title":"Computational Linguistics"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Munteanu, D. S., & Marcu, D. (2006, July). Extracting parallel sub-sentential fragments from non-parallel corpora. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (pp. 81\u201388). Association for Computational Linguistics, Sydney, Australia.","DOI":"10.3115\/1220175.1220186"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Och, F. J. (2003). Minimum error rate training in statistical machine translation. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (pp. 160\u2013167). Association for Computational Linguistics, Sapporo, Japan.","DOI":"10.3115\/1075096.1075117"},{"key":"7_CR29","unstructured":"Papineni, K., Roukos, S.,Ward, T., & Zhu, W-J. (2002). BLEU: A method for automatic evaluation of machine translation. In Proceedings of 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (pp. 311\u2013318), Philadelphia, PA."},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Rapp, R. (1995). Identifying word translations in non-parallel texts. In Proceedings of the 33rd Meeting of the Association for Computational Linguistics (pp. 320\u2013322), Cambridge, MA.","DOI":"10.3115\/981658.981709"},{"key":"7_CR31","volume-title":"Die Berechnung von Assoziatonen","author":"R Rapp","year":"1996","unstructured":"Rapp, R. (1996). Die Berechnung von Assoziatonen. Hildesheim: Olms."},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Rapp, R. (1999). Automatic identification of word translations from unrelated English and German corpora. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (pp. 519\u2013526), College Park, MD.","DOI":"10.3115\/1034678.1034756"},{"key":"7_CR33","unstructured":"Rapp, R., & Martin Vide, C. (2007). Statistical machine translation without parallel corpora. In G. Rehm, A. Witt, & L. Lemnitzer (Eds.), Datenstrukturen f\u00fcr linguistische Ressourcen und ihre Anwendungen\/Data Structures for Linguistic Resources and Applications. Proceedings of the Biennial GLDV Conference 2007 (pp. 231\u2013240). Gunter Narr Verlag, T\u00fcbingen."},{"key":"7_CR34","unstructured":"Rapp, R., & Zock, M. (2010). Automatic dictionary expansion using non-parallel corpora. In A. Fink, B. Lausen, W. Seidel, & A. Ultsch (Eds.) Advances in Data Analysis, Data Handling and Business Intelligence. Proceedings of the 32nd Annual Meeting of the GfKl, 2008. Springer, Heidelberg."},{"key":"7_CR35","unstructured":"Rapp, R., Sharoff, S., & Babych, B. (2012). Identifying word translations from comparable documents without a seed lexicon. In Proceedings of LREC 2012, Istanbul."},{"key":"7_CR36","unstructured":"Rayson, P., & Garside, R. (2000). Comparing corpora using frequency profiling. In Proceedings of the Workshop on Comparing Corpora (WCC \u201900) (Vol. 9, pp. 1\u20136)."},{"key":"7_CR37","unstructured":"Rumelhart, D. E., & McClelland, J. L. (1987). Parallel Distributed Processing. Explorations in the Microstructure of Cognition. Vol. 1: Foundations. MIT Press."},{"key":"7_CR38","unstructured":"Schmid, H. (1994). Probabilistic part-of-speech tagging using decision trees. International Conference on New Methods in Language Processing (pp. 44\u201349)."},{"key":"7_CR39","unstructured":"Sharoff, S., Kopotev, M., Erjavec, T., Feldman, A., & Divjak, D. (2008). Designing and evaluating a Russian tagset. In Proceedings of the Sixth Language Resources and Evaluation Conference, LREC 2008 (pp. 279\u2013285), Marrakech."},{"key":"7_CR40","unstructured":"Smith, J. R., Quirk, Ch., & Toutanova, K. (2010, June). Extracting parallel sentences from comparable corpora using document level alignment. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (pp. 403\u2013411), Association for Computational Linguistics, Los Angeles, CA."},{"key":"7_CR41","unstructured":"Stefanescu, D., Ion, R., & Hunsicker, S. (2012, May). Hybrid parallel sentence mining from comparable corpora. In Proceedings of the 16th Annual Conference of the European Association for Machine Translation (EAMT2012) (pp. 117\u2013128), Trento, Italy."},{"key":"7_CR42","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. In Proceedings of the 5th International Conference on Language Resources and Evaluation, Genoa, Italy."},{"key":"7_CR43","unstructured":"Tan, Ch. L., & Nagao, M. (1995). Automatic alignment of Japanese-Chinese bilingual texts. IEICE Transactions on Information and Systems, E78-D(1), 68\u201376."},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Tillmann, Ch. (2009, August). A beam-search extraction algorithm for comparable data. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers (pp. 225\u2013228), Association for Computational Linguistics, Suntec, Singapore.","DOI":"10.3115\/1667583.1667653"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Utiyama, M., & Isahara, H. (2003, July). Reliable measures for aligning Japanese-English news articles and sentences. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (pp. 72\u201379), Association for Computational Linguistics, Sapporo, Japan.","DOI":"10.3115\/1075096.1075106"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Wu, D., & Fung, P. (2005). Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora. In Proceedings of the Second International Joint Conference on Natural Language Processing (IJCNLP-2005), Jeju, Korea.","DOI":"10.1007\/11562214_23"},{"key":"7_CR48","unstructured":"Zhao, B., & Vogel, S. (2002). Adaptive parallel sentences mining from web a bilingual news collections. In Proceedings of the 2002 I.E. International Conference on Data Mining (pp. 745\u2013748), IEEE Computer Society, Maebashi City, Japan."}],"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_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T04:25:12Z","timestamp":1558412712000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99004-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783319990033","9783319990040"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99004-0_7","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"}}]}}