{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:50:50Z","timestamp":1774025450717,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642159978","type":"print"},{"value":"9783642159985","type":"electronic"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15998-5_5","type":"book-chapter","created":{"date-parts":[[2010,9,9]],"date-time":"2010-09-09T23:59:35Z","timestamp":1284076775000},"page":"27-39","source":"Crossref","is-referenced-by-count":10,"title":["Creating a Persian-English Comparable Corpus"],"prefix":"10.1007","author":[{"given":"Homa","family":"Baradaran Hashemi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azadeh","family":"Shakery","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heshaam","family":"Faili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"5","key":"5_CR1","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.knosys.2009.05.002","volume":"22","author":"A. AleAhmad","year":"2009","unstructured":"AleAhmad, A., Amiri, H., Darrudi, E., Rahgozar, M., Oroumchian, F.: Hamshahri: A standard Persian text collection. Knowledge-Based Systems\u00a022(5), 382\u2013387 (2009)","journal-title":"Knowledge-Based Systems"},{"key":"5_CR2","unstructured":"Bekavac, B., Osenova, P., Simov, K., Tadi\u0107, M.: Making monolingual corpora comparable: a case study of Bulgarian and Croatian. In: LREC, pp. 1187\u20131190 (2004)"},{"key":"5_CR3","unstructured":"Bijankhan, M.: Role of language corpora in writing grammar: introducing a computer software. Iranian Journal of Linguistics\u00a0(38), 38\u201367 (2004)"},{"key":"5_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/3-540-49653-X_12","volume-title":"Research and Advanced Technology for Digital Libraries","author":"M. Braschler","year":"1998","unstructured":"Braschler, M., Sch\u00e4uble, P.: Multilingual information retrieval based on document alignment techniques. In: Nikolaou, C., Stephanidis, C. (eds.) ECDL 1998. LNCS, vol.\u00a01513, pp. 183\u2013197. Springer, Heidelberg (1998)"},{"key":"5_CR5","first-page":"9","volume":"5","author":"N. Collier","year":"2003","unstructured":"Collier, N., Kumano, A., Hirakawa, H.: An application of local relevance feedback for building comparable corpora from news article matching. NII. J. (Natl. Inst. Inform.)\u00a05, 9\u201323 (2003)","journal-title":"NII. J. (Natl. Inst. Inform.)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Davis, M.W.: On the effective use of large parallel corpora in cross-language text retrieval. Cross-language Information Retrieval, 11\u201322 (1998)","DOI":"10.1007\/978-1-4615-5661-9_2"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Dimitrova, L., Ide, N., Petkevic, V., Erjavec, T., Kaalep, H.J., Tufis, D.: Multext-east: parallel and comparable corpora and lexicons for six central and eastern european languages. In: ACL, pp. 315\u2013319 (1998)","DOI":"10.3115\/980451.980897"},{"issue":"1","key":"5_CR8","first-page":"17","volume":"20","author":"M. Ghayoomi","year":"2010","unstructured":"Ghayoomi, M., Momtazi, S., Bijankhan, M.: A study of corpus development for Persian. International Journal of Asian Language Processing\u00a020(1), 17\u201333 (2010)","journal-title":"International Journal of Asian Language Processing"},{"key":"5_CR9","unstructured":"Karimi, S.: Machine Transliteration of Proper Names between English and Persian. Ph.D. thesis, RMIT University, Melbourne, Victoria, Australia (2008)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Koskenniemi, K.: Two-level morphology: A general computational model for word-form recognition and production. Publications of the Department of General Linguistics, University of Helsinki 11 (1983)","DOI":"10.3115\/980491.980529"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Lafferty, J., Zhai, C.: Document language models, query models, and risk minimization for information retrieval. In: SIGIR, pp. 111\u2013119 (2001)","DOI":"10.1145\/383952.383970"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"McNamee, P., Mayfield, J.: Comparing cross-language query expansion techniques by degrading translation resources. In: SIGIR, pp. 159\u2013166 (2002)","DOI":"10.1145\/564376.564406"},{"issue":"1","key":"5_CR13","doi-asserted-by":"publisher","first-page":"181","DOI":"10.7202\/029804ar","volume":"54","author":"T.M. Miangah","year":"2009","unstructured":"Miangah, T.M.: Constructing a Large-Scale English-Persian Parallel Corpus. Meta: Translators\u2019 Journal\u00a054(1), 181\u2013188 (2009)","journal-title":"Meta: Translators\u2019 Journal"},{"issue":"4","key":"5_CR14","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1162\/089120105775299168","volume":"31","author":"D. Munteanu","year":"2005","unstructured":"Munteanu, D., Marcu, D.: Improving machine translation performance by exploiting non-parallel corpora. Comput. Linguist.\u00a031(4), 477\u2013504 (2005)","journal-title":"Comput. Linguist."},{"key":"5_CR15","first-page":"223","volume":"33","author":"D. Oard","year":"1998","unstructured":"Oard, D., Diekema, A.: Cross-language information retrieval. Annual Review of Information Science and Technology\u00a033, 223\u2013256 (1998)","journal-title":"Annual Review of Information Science and Technology"},{"key":"5_CR16","unstructured":"Pilevar, M.T., Feili, H.: PersianSMT: A first attempt to english-persian statistical machine translation. In: JADT (2010)"},{"key":"5_CR17","unstructured":"Pirkola, A., Leppanen, E., J\u00e4rvelin, K.: The RATF formula (Kwok\u2019s formula): exploiting average term frequency in cross-language retrieval. Information Research 7(2) (2002)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Resnik, P.: Mining the web for bilingual text. In: ACL, pp. 527\u2013534 (1999)","DOI":"10.3115\/1034678.1034757"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Walker, S.: Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval. In: SIGIR, pp. 232\u2013241 (1994)","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"5_CR20","unstructured":"Sharoff, S.: Creating general-purpose corpora using automated search engine queries. In: WaCky! Working Papers on the Web as Corpus (2006)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Sheridan, P., Ballerini, J.P.: Experiments in multilingual information retrieval using the spider system. In: SIGIR, pp. 58\u201365 (1996)","DOI":"10.1145\/243199.243213"},{"issue":"4","key":"5_CR22","doi-asserted-by":"publisher","first-page":"257","DOI":"10.2498\/cit.2005.04.01","volume":"13","author":"R. Steinberger","year":"2005","unstructured":"Steinberger, R., Pouliquen, B., Ignat, C.: Navigating multilingual news collections using automatically extracted information. CIT\u00a013(4), 257\u2013264 (2005)","journal-title":"CIT"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Talvensaari, T., Laurikkala, J., J\u00e4rvelin, K., Juhola, M.: Creating and exploiting a comparable corpus in cross-language information retrieval. TOIS\u00a025(4) (2007)","DOI":"10.1145\/1198296.1198300"},{"key":"5_CR24","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/s10791-008-9058-8","volume":"11","author":"T. Talvensaari","year":"2008","unstructured":"Talvensaari, T., Pirkola, A., J\u00e4rvelin, K., Juhola, M., Laurikkala, J.: Focused web crawling in the acquisition of comparable corpora. Information Retrieval\u00a011, 427\u2013445 (2008)","journal-title":"Information Retrieval"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Tao, T., Zhai, C.X.: Mining comparable bilingual text corpora for cross-language information integration. In: SIGKDD, pp. 691\u2013696 (2005)","DOI":"10.1145\/1081870.1081958"},{"key":"5_CR26","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/3-540-45820-4_17","volume-title":"Machine Translation: From Research to Real Users","author":"T. Utsuro","year":"2002","unstructured":"Utsuro, T., Horiuchi, T., Chiba, Y., Hamamoto, T.: Semi-automatic compilation of bilingual lexicon entries from cross-lingually relevant news articles on WWW news sites. In: Richardson, S.D. (ed.) AMTA 2002. LNCS (LNAI), vol.\u00a02499, pp. 165\u2013176. Springer, Heidelberg (2002)"},{"issue":"6","key":"5_CR27","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1016\/j.ipm.2003.11.002","volume":"40","author":"C.C. Yang","year":"2004","unstructured":"Yang, C.C., Li, W., et al.: Building parallel corpora by automatic title alignment using length-based and text-based approaches. Information Processing & Management\u00a040(6), 939\u2013955 (2004)","journal-title":"Information Processing & Management"}],"container-title":["Lecture Notes in Computer Science","Multilingual and Multimodal Information Access Evaluation"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15998-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T06:22:59Z","timestamp":1559629379000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15998-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642159978","9783642159985"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15998-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010]]}}}