{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T17:24:26Z","timestamp":1767115466356,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,5,30]],"date-time":"2015-05-30T00:00:00Z","timestamp":1432944000000},"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":["Lang Resources &amp; Evaluation"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s10579-015-9304-9","type":"journal-article","created":{"date-parts":[[2015,5,29]],"date-time":"2015-05-29T09:59:23Z","timestamp":1432893563000},"page":"839-861","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Exploring and exploiting a historical corpus for Arabic"],"prefix":"10.1007","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5270-7409","authenticated-orcid":false,"given":"Bassam","family":"Hammo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sane","family":"Yagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omaima","family":"Ismail","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"AbuShariah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,30]]},"reference":[{"key":"9304_CR1","unstructured":"A Representative Corpus of Historical English Registers (ARCHER). (2014). http:\/\/www.alc.manchester.ac.uk\/subjects\/lel\/research\/projects\/archer\/using-archer . Accessed 15 January 2015."},{"key":"9304_CR2","unstructured":"Abb\u00e8s, R., & Dichy, J. (2008). AraConc, an Arabic concordance software based on the DIINAR.1 language resource. In The 6th international conference on informatics and systems, pp. 127\u2013134."},{"issue":"6","key":"9304_CR3","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1002\/(SICI)1097-4571(1999)50:6<524::AID-ASI7>3.0.CO;2-M","volume":"50","author":"H Abu-Salem","year":"1999","unstructured":"Abu-Salem, H., Al-Omari, M., & Evens, M. W. (1999). Stemming methodologies over individual query words for an Arabic information retrieval system. Journal of the American Society for Information Science, 50(6), 524\u2013529.","journal-title":"Journal of the American Society for Information Science"},{"key":"9304_CR4","unstructured":"Alansary, S., Nagi, M., & Adly, N. (2007). Building an international corpus of Arabic (ICA): Progress of compilation stage. In 7th international conference on language engineering, Cairo, Egypt."},{"key":"9304_CR5","unstructured":"Alansary, S., Nagi, M., & Adly, N. (2008). Towards analyzing the international corpus of Arabic (ICA): Progress of morphological stage. In 8th international conference on language engineering, Cairo, Egypt."},{"key":"9304_CR6","unstructured":"Alrabiah, M., Al-Salman, A., & Atwell, E. (2013). The design and construction of the 50 million words KSUCCA. In The proceedings of the second workshop on arabic corpus linguistics (WACL-2), Lancaster University, UK."},{"issue":"2","key":"9304_CR7","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1075\/ijcl.11.2.02als","volume":"11","author":"L Al-Sulaiti","year":"2006","unstructured":"Al-Sulaiti, L., & Atwell, E. S. (2006). The design of a corpus of contemporary Arabic. International Journal of Corpus Linguistics, 11(2), 135\u2013171.","journal-title":"International Journal of Corpus Linguistics"},{"key":"9304_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-014-9284-1","author":"AO Al-Thubaity","year":"2014","unstructured":"Al-Thubaity, A. O. (2014). A 700\u00a0M\u00a0+\u00a0Arabic corpus: KACST Arabic corpus design and construction. Language Resources and Evaluation,. doi: 10.1007\/s10579-014-9284-1 .","journal-title":"Language Resources and Evaluation"},{"key":"9304_CR9","unstructured":"Attia, M., Pecina, P., Tounsi, L., Toral, A., & van Genabith, J. (2011). Lexical profiling for Arabic. In Proceedings of eLex, pp. 23\u201333."},{"key":"9304_CR10","doi-asserted-by":"crossref","unstructured":"Boella, M., Romani, F., Al-Raies, A., Solimando, C., & Lancioni, G. (2011). The SALAH project: Segmentation and linguistic analysis of \u1e24ad\u012b\u1e6f Arabic texts. Information Retrieval Technology, pp. 538\u2013549.","DOI":"10.1007\/978-3-642-25631-8_49"},{"key":"9304_CR11","unstructured":"Buckwalter, T. (2004). Buckwalter Arabic morphological analyzer version 2.0 linguistic data consortium, Philadelphia. http:\/\/www.qamus.org\/morphology.htm . Accessed 15 January 2015."},{"key":"9304_CR12","volume-title":"Tarikh Al-Adab Al-Arabi: Al-Asr Al-Jahili","author":"Shawqi Dhaif","year":"1986","unstructured":"Dhaif, Shawqi. (1986). Tarikh Al-Adab Al-Arabi: Al-Asr Al-Jahili. Cairo: Dar Al-Maarif."},{"key":"9304_CR13","unstructured":"Dukes, K., & Habash, N. (2010). Morphological annotation of Quranic Arabic. In LREC."},{"key":"9304_CR14","doi-asserted-by":"crossref","unstructured":"Hajjar, M., Al-Hajjar, A., Zreik, K., & Gallinari, P. (2010). An improved structured and progressive electronic dictionary for the Arabic language: iSPEDAL. In Fifth international conference on internet and web applications and services (ICIW), pp. 489\u2013495.","DOI":"10.1109\/ICIW.2010.80"},{"issue":"3","key":"9304_CR15","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s10791-008-9081-9","volume":"12","author":"B Hammo","year":"2009","unstructured":"Hammo, B. (2009). Towards enhancing retrieval effectiveness of search engines for diacritisized Arabic documents. Information Retrieval, 12(3), 300\u2013323.","journal-title":"Information Retrieval"},{"issue":"4","key":"9304_CR16","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s10579-004-1917-3","volume":"38","author":"B Hammo","year":"2004","unstructured":"Hammo, B., Abuleil, S., Lytinen, S., & Evens, M. (2004). Experimenting with a question answering system for the Arabic language. Computers and the Humanities, 38(4), 397\u2013415.","journal-title":"Computers and the Humanities"},{"key":"9304_CR17","doi-asserted-by":"crossref","unstructured":"Hammo, B., Abu-Salem, H., & Lytinen, S. (2002). QARAB: A question answering system to support the Arabic language. In Proceedings of the ACL-02 workshop on computational approaches to Semitic languages, pp. 1\u201311.","DOI":"10.3115\/1118637.1118644"},{"key":"9304_CR18","unstructured":"Hammo, B., Al-Shargi, F., Yagi, S. & Obeid, N. (2013). Developing tools for Arabic corpus for researchers. In The proceedings of the second workshop on Arabic corpus linguistics (WACL-2), Lancaster University, UK."},{"key":"9304_CR19","unstructured":"Helsinki Corpus of English Texts. (2011). Department of Modern Languages, University of Helsinki. http:\/\/www.helsinki.fi\/varieng\/CoRD\/corpora\/HelsinkiCorpus\/HC_XML.html . Accessed 15 January 2015."},{"key":"9304_CR20","volume-title":"A history of the Arab peoples: Updated edition","author":"A Hourani","year":"2013","unstructured":"Hourani, A. (2013). A history of the Arab peoples: Updated edition. London: Faber and Faber."},{"key":"9304_CR21","unstructured":"Ide, N., Patrice, B., & Laurent, R. (2000). XCES: An XML-based standard for linguistic corpora. In Proceedings of the second language resources and evaluation conference (LREC)."},{"key":"9304_CR22","volume-title":"Stemming Arabic text","author":"S Khoja","year":"1999","unstructured":"Khoja, S., & Garside, R. (1999). Stemming Arabic text. Computing Department, Lancaster University: Lancaster."},{"key":"9304_CR23","volume-title":"Historical semantics and cognition","author":"E K\u00f6nig","year":"1999","unstructured":"K\u00f6nig, E., & Siemund, P. (1999). Intensifiers as targets and sources of semantic change. In Andreas Blank & Peter Koch (Eds.), Historical semantics and cognition. Berlin: Walter de Gruyter."},{"key":"9304_CR24","volume-title":"Frequency analysis of English usage: Lexicon and grammar","author":"FW Nelson","year":"1982","unstructured":"Nelson, F. W., & Ku\u0109era, H. (1982). Frequency analysis of English usage: Lexicon and grammar. Boston: Houghton Mifflin."},{"issue":"1","key":"9304_CR25","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1093\/llc\/fqm044","volume":"23","author":"T Pilz","year":"2008","unstructured":"Pilz, T., Ernst-Gerlach, A., Kempken, S., Rayson, P., & Archer, D. (2008). The identification of spelling variants in English and German historical texts: Manual or automatic? Literary and Linguistic Computing, 23(1), 65\u201372.","journal-title":"Literary and Linguistic Computing"},{"issue":"2","key":"9304_CR26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00436ED1V01Y201207HLT017","volume":"5","author":"M Piotrowski","year":"2012","unstructured":"Piotrowski, M. (2012). Natural language processing for historical texts. Synthesis Lectures on Human Language Technologies, 5(2), 1\u2013157.","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"9304_CR27","unstructured":"Rayson, P., Archer, D., Baron, A., Culpeper, J., & Smith, N. (2007). Tagging the bard: Evaluating the accuracy of a modern POS tagger on early modern English corpora. In Proceedings of corpus linguistics 2007, University of Birmingham, UK."},{"issue":"1","key":"9304_CR28","doi-asserted-by":"crossref","first-page":"39","DOI":"10.3366\/cor.2006.1.1.39","volume":"1","author":"A Roberts","year":"2006","unstructured":"Roberts, A., Al-Sulaiti, L., & Atwell, E. (2006). aConCorde: Towards an open-source, extendable concordancer for Arabic. Corpora, 1(1), 39\u201360.","journal-title":"Corpora"},{"key":"9304_CR29","unstructured":"R\u00f6gnvaldsson, E., & Helgad\u00f3ttir, S. (2008). Morphological tagging of Old Norse texts and its use in studying syntactic variation and change. In Proceedings of the LREC 2008 workshop on language technology for cultural heritage data (LaTeCH 2008). ELRA, Paris."},{"key":"9304_CR30","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24, 513\u2013523.","journal-title":"Information Processing and Management"},{"key":"9304_CR31","unstructured":"S\u00e1nchez-Marco, C., Boleda Torrent, G., Fontana, J. M., & Domingo, J. (2010). Annotation and representation of a diachronic corpus of Spanish. In Proceedings of the seventh conference on international language resources and evaluation (LREC\u201910), Malta."},{"key":"9304_CR32","volume-title":"The legacy of Islam","author":"J Schacht","year":"1974","unstructured":"Schacht, J., & Bosworth, C. E. (1974). The legacy of Islam. Oxford: Oxford University Press."},{"key":"9304_CR33","unstructured":"Sharaf, A. & Atwell, E. (2012). QurAna: Corpus of the Quran annotated with Pronominal Anaphora. In LREC, pp. 130\u2013137."},{"key":"9304_CR34","doi-asserted-by":"crossref","unstructured":"Toutanova, K., Klein, D., Manning, C., & Singer, Y. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network. In Proceedings of HLT-NAACL 2003, pp. 252\u2013259.","DOI":"10.3115\/1073445.1073478"},{"key":"9304_CR35","unstructured":"Yagi, S. & Ghodhaya, M. (2014). Culture from a historical semantic perspective. Al-Majalla Al-Thaqafiya, 85, University of Jordan, pp. 86\u2013119."},{"key":"9304_CR36","doi-asserted-by":"crossref","unstructured":"Yang, Y. M. (1995). Noise reduction in a statistical approach to text categorization. In Proceedings of SIGIR-95, 18th ACM international conference on research and development in information retrieval, pp. 256\u2013263.","DOI":"10.1145\/215206.215367"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-015-9304-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-015-9304-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-015-9304-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-015-9304-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T16:13:29Z","timestamp":1566749609000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-015-9304-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,30]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["9304"],"URL":"https:\/\/doi.org\/10.1007\/s10579-015-9304-9","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2015,5,30]]}}}