{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:00:33Z","timestamp":1742943633653,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319690049"},{"type":"electronic","value":"9783319690056"}],"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-69005-6_37","type":"book-chapter","created":{"date-parts":[[2017,10,6]],"date-time":"2017-10-06T05:17:45Z","timestamp":1507267065000},"page":"449-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harvest Uyghur-Chinese Aligned-Sentences Bitexts from Multilingual Sites Based on Word Embedding"],"prefix":"10.1007","author":[{"given":"ShaoLin","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Xiao","family":"Li","sequence":"additional","affiliation":[]},{"given":"YaTing","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"ChengGang","family":"Mi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,7]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.2478\/v10108-010-0003-9","volume":"93","author":"M Espla-Gomis","year":"2010","unstructured":"Espla-Gomis, M., Forcada, M.L.: Combining content-based and URL-based heuristics to harvest aligned bitexts from multilingual sites with bitextor. Prague Bull. Math. Linguist. 93, 77\u201386 (2010)","journal-title":"Prague Bull. Math. Linguist."},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, K., Gao, J., Vines, P.: Automatic acquisition of Chinese\u2013English parallel corpus from the web. In: Advances in Information Retrieval, vol. 3936, pp. 420\u2013431 (2006)","DOI":"10.1007\/11735106_37"},{"key":"37_CR3","unstructured":"San Vicente, I., Manterola, I.: PaCo2: a fully automated tool for gathering parallel corpora from the web. In: Proceedings of the 8th International Conference on Language Resources and Evaluation, pp. 1\u20136 (2012)"},{"key":"37_CR4","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1162\/089120103322711578","volume":"29","author":"P Resnik","year":"2003","unstructured":"Resnik, P., Smith, N.A.: The Web as a parallel corpus. Comput. Linguist. 29, 349\u2013380 (2003)","journal-title":"Comput. Linguist."},{"key":"37_CR5","unstructured":"Papavassiliou, V., Prokopidis, P., Thurmair, G.: A modular open-source focused crawler for mining monolingual and bilingual corpora from the web. In: Proceedings of the Sixth Workshop on Building and Using Comparable Corpora, pp. 43\u201351 (2013)"},{"key":"37_CR6","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"DS Munteanu","year":"2005","unstructured":"Munteanu, D.S., Marcu, D.: Improving machine translation performance by exploiting non-parallel corpora. Comput. Linguist. 31, 477\u2013504 (2005a)","journal-title":"Comput. Linguist."},{"key":"37_CR7","unstructured":"Espla-Gomis, M.: Bitextor, a free\/open-source software to harvest translation memories from multilingual websites. In: Beyond Translation Memories Workshop (MT Summit XII) (2009)"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Espla-Gomis, M., Forcada, M.L.: Bitextor\u2019s participation in WMT\u201916: shared task on document alignment. In: Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers, pp. 685\u2013691 (2016)","DOI":"10.18653\/v1\/W16-2367"},{"key":"37_CR9","unstructured":"Ma, X., Liberman, M.Y.: BITS: a method for bilingual text search over the web. Linguist. Data Consort., 538\u2013542 (1999)"},{"key":"37_CR10","unstructured":"Espla-Gomis, M., Klubicka, F., Ljube, N.: Comparing two acquisition systems for automatically building an English\u2013Croatian parallel corpus from multilingual websites. In: LREC 2014 Proceedings, pp. 1252\u20131256 (2014)"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Nie, J.-Y., Simard, M., Isabelle, P., Durand, R.: Cross-language information retrieval based on parallel texts and automatic mining of parallel texts from the Web. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 74\u201381 (1999)","DOI":"10.1145\/312624.312656"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Ling, W., Marujo, L., Dyer, C., Black, A., Trancoso, I.: Crowdsourcing high-quality parallel data extraction from Twitter. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 426\u2013436 (2014)","DOI":"10.3115\/v1\/W14-3356"},{"key":"37_CR13","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"DS Munteanu","year":"2005","unstructured":"Munteanu, D.S., Marcu, D.: Improving machine translation performance by exploiting non-parallel corpora. Comput. Linguist. 31, 477\u2013504 (2005b)","journal-title":"Comput. Linguist."},{"key":"37_CR14","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR Workshop, pp. 1\u201312 (2013a)"},{"key":"37_CR15","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111\u20133119 (2013b)"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-69005-6_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T05:35:40Z","timestamp":1570167340000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-69005-6_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319690049","9783319690056"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-69005-6_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}