{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:40:10Z","timestamp":1751848810269,"version":"3.41.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007935"},{"type":"electronic","value":"9783030007942"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-00794-2_9","type":"book-chapter","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T19:50:24Z","timestamp":1536349824000},"page":"84-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adjusting Machine Translation Datasets for Document-Level Cross-Language Information Retrieval: Methodology"],"prefix":"10.1007","author":[{"given":"Gennady","family":"Shtekh","sequence":"first","affiliation":[]},{"given":"Polina","family":"Kazakova","sequence":"additional","affiliation":[]},{"given":"Nikita","family":"Nikitinsky","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Ballesteros, L., Croft, W.B.: Phrasal translation and query expansion techniques for cross-language information retrieval. In: ACM SIGIR Forum, vol. 31, pp. 84\u201391. ACM (1997)","DOI":"10.1145\/278459.258540"},{"issue":"6","key":"9_CR2","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/BF01829874","volume":"29","author":"MW Berry","year":"1995","unstructured":"Berry, M.W., Young, P.G.: Using latent semantic indexing for multilanguage information retrieval. Comput. Hum. 29(6), 413\u2013429 (1995)","journal-title":"Comput. Hum."},{"key":"9_CR3","unstructured":"Boyd-Graber, J., Blei, D.M.: Multilingual topic models for unaligned text. In: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 75\u201382. AUAI Press (2009)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Braschler, M., Harman, D., Hess, M., Kluck, M., Peters, C., Sch\u00e4uble, P.: The evaluation of systems for cross-language information retrieval. In: LREC (2000)","DOI":"10.6028\/NIST.SP.500-246.xlingual-overview"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"De Meo, P., Ferrara, E., Fiumara, G., Provetti, A.: Generalized Louvain method for community detection in large networks. In: 2011 11th International Conference on Intelligent Systems Design and Applications, ISDA, pp. 88\u201393. IEEE (2011)","DOI":"10.1109\/ISDA.2011.6121636"},{"key":"9_CR6","unstructured":"Dumais, S.T., Letsche, T.A., Littman, M.L., Landauer, T.K.: Automatic cross-language retrieval using latent semantic indexing. In: AAAI Spring Symposium on Cross-Language Text and Speech Retrieval, vol. 15, p. 21 (1997)"},{"key":"9_CR7","unstructured":"Ferrero, J., Agnes, F., Besacier, L., Schwab, D.: A multilingual, multi-style and multi-granularity dataset for cross-language textual similarity detection. In: 10th Edition of the Language Resources and Evaluation Conference (2016)"},{"key":"9_CR8","unstructured":"Germann, U.: Aligned hansards of the 36th parliament of Canada (2001). https:\/\/www.isi.edu\/natural-language\/download\/hansard\/"},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-94-017-1491-4_5","volume-title":"EuroWordNet: A Multilingual Database with Lexical Semantic Networks","author":"J Gonzalo","year":"1998","unstructured":"Gonzalo, J., Verdejo, F., Peters, C., Calzolari, N.: Applying EuroWordNet to cross-language text retrieval. In: Vossen, P. (ed.) EuroWordNet: A Multilingual Database with Lexical Semantic Networks, pp. 113\u2013135. Springer, Dordrecht (1998). https:\/\/doi.org\/10.1007\/978-94-017-1491-4_5"},{"key":"9_CR10","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. arXiv preprint arXiv:1702.08734 (2017)"},{"key":"9_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-3-540-85902-4_2","volume-title":"Focused Access to XML Documents","author":"J Kamps","year":"2008","unstructured":"Kamps, J., Pehcevski, J., Kazai, G., Lalmas, M., Robertson, S.: INEX 2007 evaluation measures. In: Fuhr, N., Kamps, J., Lalmas, M., Trotman, A. (eds.) INEX 2007. LNCS, vol. 4862, pp. 24\u201333. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-85902-4_2"},{"key":"9_CR12","unstructured":"Koehn, P.: Europarl: a parallel corpus for statistical machine translation. In: MT Summit, vol. 5, pp. 79\u201386 (2005)"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Kulesza, A., Taskar, B., et al.: Determinantal point processes for machine learning. Found. Trends$${\\textregistered }$$ Mach. Learn. 5(2\u20133), 123\u2013286 (2012)","DOI":"10.1561\/2200000044"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Meng, H.M., Lo, W.K., Chen, B., Tang, K.: Generating phonetic cognates to handle named entities in English-Chinese cross-language spoken document retrieval. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001, pp. 311\u2013314. IEEE (2001)","DOI":"10.1109\/ASRU.2001.1034649"},{"key":"9_CR15","unstructured":"Mori, T., Kokubu, T., Tanaka, T.: Cross-lingual information retrieval based on LSI with multiple word spaces. In: Proceedings of the 2nd NTCIR Workshop Meeting on Evaluation of Chinese & Japanese Text Retrieval and Text Summarization. Citeseer (2001)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Nikitinsky, N., Ustalov, D., Shashev, S.: An information retrieval system for technology analysis and forecasting. In: Artificial Intelligence and Natural Language and Information Extraction, Social Media and Web Search FRUCT Conference, AINL-ISMW FRUCT, pp. 52\u201359. IEEE (2015)","DOI":"10.1109\/AINL-ISMW-FRUCT.2015.7382969"},{"key":"9_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/3-540-49478-2_42","volume-title":"Machine Translation and the Information Soup","author":"DW Oard","year":"1998","unstructured":"Oard, D.W.: A comparative study of query and document translation for cross-language information retrieval. In: Farwell, D., Gerber, L., Hovy, E. (eds.) AMTA 1998. LNCS, vol. 1529, pp. 472\u2013483. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/3-540-49478-2_42"},{"issue":"3\u20134","key":"9_CR18","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/A:1011994105352","volume":"4","author":"A Pirkola","year":"2001","unstructured":"Pirkola, A., Hedlund, T., Keskustalo, H., J\u00e4rvelin, K.: Dictionary-based cross-language information retrieval: problems, methods, and research findings. Inf. Retr. 4(3\u20134), 209\u2013230 (2001)","journal-title":"Inf. Retr."},{"key":"9_CR19","unstructured":"Ruder, S.: A survey of cross-lingual embedding models. arXiv preprint arXiv:1706.04902 (2017)"},{"key":"9_CR20","volume-title":"TREC: Experiment and Evaluation in Information Retrieval","author":"EM Voorhees","year":"2005","unstructured":"Voorhees, E.M., Harman, D.K., et al.: TREC: Experiment and Evaluation in Information Retrieval, vol. 1. MIT Press, Cambridge (2005)"},{"issue":"3","key":"9_CR21","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10791-012-9200-5","volume":"16","author":"I Vuli\u0107","year":"2013","unstructured":"Vuli\u0107, I., De Smet, W., Moens, M.F.: Cross-language information retrieval models based on latent topic models trained with document-aligned comparable corpora. Inf. Retr. 16(3), 331\u2013368 (2013)","journal-title":"Inf. Retr."},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Vuli\u0107, I., Moens, M.F.: Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 363\u2013372. ACM (2015)","DOI":"10.1145\/2766462.2767752"},{"key":"9_CR23","unstructured":"Ziemski, M., Junczys-Dowmunt, M., Pouliquen, B.: The united nations parallel corpus v1.0. In: LREC (2016)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00794-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:27:18Z","timestamp":1751848038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00794-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007935","9783030007942"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00794-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}