{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:38:58Z","timestamp":1779899938043,"version":"3.53.1"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,4,12]],"date-time":"2019-04-12T00:00:00Z","timestamp":1555027200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Qatar Computing Research Institute"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10579-019-09460-w","type":"journal-article","created":{"date-parts":[[2019,4,12]],"date-time":"2019-04-12T17:04:13Z","timestamp":1555088653000},"page":"771-805","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Studying the history of the Arabic language: language technology and a large-scale historical corpus"],"prefix":"10.1007","volume":"53","author":[{"given":"Yonatan","family":"Belinkov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Magidow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Barr\u00f3n-Cede\u00f1o","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avi","family":"Shmidman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxim","family":"Romanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,12]]},"reference":[{"key":"9460_CR1","doi-asserted-by":"publisher","unstructured":"Abdelali, A., Darwish, K., Durrani, N., & Mubarak, H. (2016). Farasa: A fast and furious segmenter for Arabic. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Demonstrations (pp. 11\u201316). Association for Computational Linguistics, http:\/\/aclanthology.coli.uni-saarland.de\/pdf\/N\/N16\/N16-3003.pdf . https:\/\/doi.org\/10.18653\/v1\/N16-3003 . Accessed 11 Apr 2019.","DOI":"10.18653\/v1\/N16-3003"},{"key":"9460_CR2","doi-asserted-by":"crossref","unstructured":"Al-Jallad, A. (2015). An outline of the grammar of the Safaitic inscriptions. No.\u00a080 in Studies in Semitic languages and linguistics. Brill","DOI":"10.1163\/9789004289826"},{"key":"9460_CR3","unstructured":"Al-Sulaiti, L. (2004). Designing and developing a corpus of contemporary Arabic. Master\u2019s thesis, The University of Leeds, Leeds, UK"},{"issue":"3","key":"9460_CR4","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/s10579-014-9284-1","volume":"49","author":"AO Al-Thubaity","year":"2015","unstructured":"Al-Thubaity, A. O. (2015). A 700M+ Arabic corpus: KACST Arabic corpus design and construction. Language Resources and Evaluation, 49(3), 721\u2013751.","journal-title":"Language Resources and Evaluation"},{"key":"9460_CR5","volume-title":"A linguistic study of the development of scientific vocabulary in standard Arabic","author":"ASM Ali","year":"1987","unstructured":"Ali, A. S. M. (1987). A linguistic study of the development of scientific vocabulary in standard Arabic. New York: Kegan Paul International."},{"key":"9460_CR6","unstructured":"Alrabiah, M., Al-Salman, A., Atwell, E. (2013). The design and construction of the 50 million words KSUCCA. In Proceedings of WACL2 second workshop on Arabic corpus linguistics (pp. 5\u20138)."},{"issue":"4","key":"9460_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.jksuci.2014.06.009","volume":"26","author":"T Arts","year":"2014","unstructured":"Arts, T., Belinkov, Y., Habash, N., Kilgarriff, A., & Suchomel, V. (2014). arTenTen: Arabic corpus and word sketches. Journal of King Saud University\u2014Computer and Information Sciences, 26(4), 357\u2013371. (Special Issue on Arabic NLP).","journal-title":"Journal of King Saud University\u2014Computer and Information Sciences"},{"key":"9460_CR8","unstructured":"Basile, C., Benedetto, D., Caglioti, G., Degli & Esposti, M. (2009). A plagiarism detection procedure in three steps: Selection, matches and squares. In B. Stein, P. Rosso, E. Stamatatos, M. Koppel, & E. Agirre (Eds.), SEPLN 2009 workshop on uncovering plagiarism, authorship, and social software misuse (PAN 2009) (Vol. 502, pp. 19\u201323). CEUR-WS.org, San Sebastian, Spain, http:\/\/ceur-ws.org\/Vol-502 . Accessed 11 Apr 2019."},{"key":"9460_CR9","unstructured":"Belinkov, Y., Magidow, A., Romanov, M., Shmidman, A., Koppel, M. (2016). Shamela: A large-scale historical Arabic corpus. In Proceedings of the workshop on language technology resources and tools for digital humanities (LT4DH at Coling) (pp. 45\u201353). The COLING 2016 Organizing Committee, Osaka, Japan."},{"key":"9460_CR10","unstructured":"Bensalem, I., Boukhalfa, I., Rosso, P., Lahsen, A., Darwish, K., & Chikhi, S. (2015). Overview of the AraPlagDet PAN@ FIRE2015 shared task on Arabic plagiarism detection. In Notebook Papers of FIRE 2015 (CEUR-WS), Gandhinagar, India (Vol. 1587, pp. 111\u2013122)."},{"key":"#cr-split#-9460_CR11.1","unstructured":"Bj\u00f6rkelund, A., \u00c7etino\u011flu, \u00d6., Farkas, R., Mueller, T., & Seeker, W. (2013)."},{"key":"#cr-split#-9460_CR11.2","unstructured":"(Re) Ranking meets morphosyntax: State-of-the-art results from the SPMRL 2013 shared task (pp. 135-145)."},{"key":"9460_CR12","unstructured":"Braschler, M., & Harman, D. (Eds.). (2010). Notebook papers of CLEF 2010 LABs and workshops, Padua, Italy."},{"key":"9460_CR13","unstructured":"Chambers, N. (2012) Labeling documents with timestamps: Learning from their time expressions. In Proceedings of the 50th annual meeting of the association for computational linguistics, Jeju Island, Korea (Vol. 1: Long Papers, pp. 98\u2013106)."},{"key":"9460_CR14","first-page":"242","volume-title":"Corpus linguistics: An international handbook","author":"C Claridge","year":"2008","unstructured":"Claridge, C. (2008). Historical corpora. In A. L\u00fcdeling & M. Kyt\u00f6 (Eds.), Corpus linguistics: An international handbook (Vol. 1, pp. 242\u2013259). Berlin: Walter de Gruyter."},{"key":"9460_CR15","first-page":"1249","volume-title":"Handbook of corpus linguistics, handbooks of linguistics and communication science","author":"P Clough","year":"2009","unstructured":"Clough, P., & Gaizauskas, R. (2009). Corpora and text re-use. In A. L\u00fcdeling, M. Kyt\u00f6, & T. McEnery (Eds.), Handbook of corpus linguistics, handbooks of linguistics and communication science (pp. 1249\u20131271). Berlin: Mouton de Gruyter."},{"key":"9460_CR16","unstructured":"Clough, P., Gaizauskas, R., Piao, S., & Wilks, Y. (2002). Measuring text reuse. In Proceedings of the 40th annual meeting of the association for computational linguistics (ACL 2002) (pp. 152\u2013159). Philadelphia, PA: Association for Computational Linguistics."},{"key":"9460_CR17","unstructured":"Dalli, A., & Wilks, Y. (2006). Automatic dating of documents and temporal text classification. In Proceedings of the workshop on annotating and reasoning about time and events, Sydney, Australia (pp. 17\u201322)."},{"key":"9460_CR18","unstructured":"Darwish, K., Abdelali, A., & Mubarak, H. (2014). Using stem-templates to improve Arabic POS and gender\/number tagging. In Proceedings of the 9th international conference on language resources and evaluation (LREC\u201914), LREC 2014 (pp. 2926\u20132931). European Language Resources Association (ELRA), http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/335_Paper.pdf . Accessed 11 Apr 2019."},{"key":"9460_CR19","unstructured":"Darwish, K., & Mubarak, H. (2016). Farasa: A new fast and accurate Arabic word segmenter. In LREC."},{"key":"9460_CR20","unstructured":"Darwish, K., Mubarak, H., Abdelali, A., & Eldesouki, M. (2017). Arabic POS tagging: Don\u2019t abandon feature engineering just yet. In Proceedings of the 3rd Arabic natural language processing workshop (pp. 130\u2013137). Association for Computational Linguistics, http:\/\/aclweb.org\/anthology\/W17-1316 . Accessed 11 Apr 2019."},{"key":"9460_CR21","unstructured":"Davies, M. (2010). The corpus of historical American English: 400 million words, 1810\u20132009, http:\/\/corpus.byu.edu\/coha . Accessed 11 Apr 2019."},{"key":"9460_CR22","unstructured":"de\u00a0Jong, F., Rode, H., & Hiemstra, D. (2005). Temporal language models for the disclosure of historical text. In Humanities, computers and cultural heritage: Proceedings of the XVI international conference of the association for history and computing (pp. 161\u2013168)."},{"key":"9460_CR23","unstructured":"Dubossarsky, H., Tsvetkov, Y., Dyer, C., & Grossman, E. (2015). A bottom up approach to category mapping and meaning change. In: V.\u00a0Pirrelli, C.\u00a0Marzi, & M.\u00a0Ferro (Eds.), Proceedings of the NetWordS final conference on word structure and word usage."},{"key":"9460_CR24","unstructured":"Elewa, A. H. (2004). Collocation and synonymy in classical Arabic: A corpus-based approach. Ph.D. Thesis, The University of Manchester, Manchester, UK"},{"key":"9460_CR25","first-page":"604","volume-title":"Encyclopedia of Arabic language and linguistics","author":"I Ferrando","year":"2007","unstructured":"Ferrando, I. (2007). History of Arabic. In K. Versteegh (Ed.), Encyclopedia of Arabic language and linguistics (Vol. 2, pp. 604\u2013611). Leiden: Brill."},{"key":"9460_CR26","first-page":"397","volume-title":"Encyclopedia of Arabic language and lingusitics","author":"W Fischer","year":"2006","unstructured":"Fischer, W. (2006). Classical Arabic. In K. Versteegh (Ed.), Encyclopedia of Arabic language and lingusitics (Vol. 1, pp. 397\u2013405). Leiden: Brill."},{"key":"9460_CR27","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1093\/oxfordhb\/9780199922765.013.0014","volume-title":"The Oxford Handbook of the history of english","author":"ST Gries","year":"2012","unstructured":"Gries, S. T., & Hilpert, M. (2012). Variability-based neighbor clustering: A bottom-up approach to periodization in historical linguistics. In T. Nevalainen & E. C. Traugott (Eds.), The Oxford Handbook of the history of english (pp. 134\u2013144). Oxford: Oxford University Press."},{"key":"9460_CR28","unstructured":"Grozea, C., & Popescu, M. (2011). The ENCOPLOT similarity measure for automatic detection of plagiarism\u2014Notebook for PAN at CLEF 2011. In: V.\u00a0Petras, P.\u00a0Forner, & P.\u00a0Clough (Eds.), Notebook papers of CLEF 2011LABs and workshops, Amsterdam, The Netherlands."},{"key":"9460_CR29","doi-asserted-by":"crossref","unstructured":"Habash, N., & Rambow, O. (2005). Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In Proceedings of ACL.","DOI":"10.3115\/1219840.1219911"},{"key":"9460_CR30","unstructured":"Habash, N., Rambow, O., & Roth, R. (2009). MADA+TOKAN: A toolkit for arabic tokenization, diacritization, morphological disambiguation, pos tagging, stemming and lemmatization. In Proceedings of the 2nd international conference on Arabic language resources and tools."},{"key":"9460_CR31","doi-asserted-by":"crossref","unstructured":"Hall, D. L. W., Durrett, G., & Klein, D. (2014). Less grammar, more features. In Proceedings of the 52nd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (pp. 228\u2013237).","DOI":"10.3115\/v1\/P14-1022"},{"key":"9460_CR32","doi-asserted-by":"publisher","unstructured":"Hamilton, W. L., Leskovec, J., & Jurafsky, D. (2016). Diachronic word embeddings reveal statistical laws of semantic change. In Proceedings of the 54th annual meeting of the association for computational linguistics (Vol. 1: Long Papers, pp. 1489\u20131501). Association for Computational Linguistics, http:\/\/aclanthology.coli.uni-saarland.de\/pdf\/P\/P16\/P16-1141.pdf . https:\/\/doi.org\/10.18653\/v1\/P16-1141 .","DOI":"10.18653\/v1\/P16-1141"},{"issue":"4","key":"9460_CR33","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1007\/s10579-015-9304-9","volume":"50","author":"B Hammo","year":"2016","unstructured":"Hammo, B., Yagi, S., Ismail, O., & AbuShariah, M. (2016). Exploring and exploiting a historical corpus for Arabic. Language Resources and Evaluation, 50(4), 839\u2013861. https:\/\/doi.org\/10.1007\/s10579-015-9304-9 .","journal-title":"Language Resources and Evaluation"},{"key":"9460_CR34","volume-title":"Modern Arabic: Structures, functions, and varieties","author":"C Holes","year":"2004","unstructured":"Holes, C. (2004). Modern Arabic: Structures, functions, and varieties. Washington, DC: Georgetown University Press."},{"issue":"2","key":"9460_CR35","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1093\/llc\/fqq002","volume":"25","author":"M Ji","year":"2010","unstructured":"Ji, M. (2010). A corpus-based study of lexical periodization in historical Chinese. Literary and Linguistic Computing, 25(2), 199\u2013213.","journal-title":"Literary and Linguistic Computing"},{"key":"9460_CR36","unstructured":"Joachims, T. (2006). Training linear SVMs in linear time. In KDD\u201906 (pp. 217\u2013226). New York, NY: ACM."},{"key":"9460_CR37","unstructured":"Kasprzak, J., & Brandejs, M. (2010). Improving the reliability of the plagiarism detection system. Lab Report for PAN at CLEF 2010. In M. Braschler, & D. Harman, (Eds.), Notebook papers of CLEF 2010 LABs and workshops, Padua, Italy."},{"key":"9460_CR38","unstructured":"Kilgarriff, A., Rychly, P., Smrz, P., & Tugwell, D. (2004). The sketch engine. In Proceedings of EURALEX."},{"key":"9460_CR39","unstructured":"Kim, Y., Chiu, Y. I., Hanaki, K., Hegde, D., & Petrov, S. (2014). Temporal analysis of language through neural language models. In Proceedings of the ACL 2014 workshop on language technologies and computational social science (pp. 61\u201365). Baltimore, MD, USA: Association for Computational Linguistics, http:\/\/www.aclweb.org\/anthology\/W14-2517 . Accessed 11 Apr 2019."},{"key":"9460_CR40","doi-asserted-by":"crossref","unstructured":"Kulkarni, V., Al-Rfou, R., Perozzi, B., & Skiena, S. (2015). Statistically significant detection of linguistic change. In Proceedings of the 24th international world wide web conference, WWW\u201915.","DOI":"10.1145\/2736277.2741627"},{"key":"9460_CR41","unstructured":"Lane, E. W. (1863). Arabic-English Lexicon. Willams & Norgate."},{"key":"9460_CR42","first-page":"87","volume-title":"Encyclopedia of Arabic language and linguistics","author":"J Lentin","year":"2006","unstructured":"Lentin, J. (2006). Middle Arabic. In K. Versteegh (Ed.), Encyclopedia of Arabic language and linguistics (Vol. 1, pp. 87\u201396). Leiden: Brill."},{"key":"9460_CR43","unstructured":"Li, W. P. (2016). Language technologies for understanding law, politics, and public policy. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MA, USA"},{"key":"9460_CR44","first-page":"239","volume":"16","author":"A Magidow","year":"2016","unstructured":"Magidow, A. (2016). A digital philological investigation of the history of h\u0101 hun\u0101 constructions. Romano-Arabica, 16, 239\u2013256.","journal-title":"Romano-Arabica"},{"key":"9460_CR45","unstructured":"Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013a). Efficient estimation of word representations in vector space. CoRR abs\/1301.3781. http:\/\/arxiv.org\/abs\/1301.3781 . Accessed 11 Apr 2019."},{"key":"9460_CR46","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013b). Distributed representations of words and phrases and their compositionality. CoRR abs\/1310.4546. http:\/\/arxiv.org\/abs\/1310.4546 . Accessed 11 Apr 2019."},{"key":"9460_CR47","unstructured":"Mikolov, T., Yih, W., & Zweig, G. (2013c). Linguistic regularities in continuous space word representations. In Proceedings of the 2013 conference of the North American Chapter of the association for computational linguistics: Human language technologies (NAACL-HLT-2013). Association for Computational Linguistics, http:\/\/research.microsoft.com\/apps\/pubs\/default.aspx?id=189726 . Accessed 11 Apr 2019."},{"key":"9460_CR48","unstructured":"Mikolov, T., Yih, W., & Zweig, G. (2013d). Linguistic regularities in continuous space word representations. In Human language technologies: Conference of the North American chapter of the association of computational linguistics, proceedings, June 9\u201314, 2013 (pp. 746\u2013751). Atlanta, Georgia, USA: Westin Peachtree Plaza Hotel, http:\/\/aclweb.org\/anthology\/N\/N13\/N13-1090.pdf . Accessed 11 Apr 2019."},{"key":"9460_CR49","unstructured":"Muhr, M., Kern, R., Zechner, M., & Granitzer, M. (2010) External and intrinsic plagiarism detection using a cross-lingual retrieval and segmentation system. In M. Braschler, & D. Harman (Eds.), Notebook papers of CLEF 2010 LABs and workshops, Padua, Italy."},{"key":"9460_CR50","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1093\/oxfordhb\/9780199764136.013.0021","volume-title":"The Oxford Handbook of Arabic linguistics","author":"DL Newman","year":"2013","unstructured":"Newman, D. L. (2013). The Arabic literary language: The nah\u1e0da and beyond. In J. Owens (Ed.), The Oxford Handbook of Arabic linguistics (pp. 472\u2013494). Oxford: Oxford University Press."},{"key":"9460_CR51","unstructured":"Niculae, V., Zampieri, M., Dinu, L., & Ciobanu, A. M. (2014). Temporal text ranking and automatic dating of texts. In Proceedings of the 14th conference of the European chapter of the association for computational linguistics, Gothenburg, Sweden (Vol. 2: Short Papers, pp. 17\u201321), http:\/\/www.aclweb.org\/anthology\/E14-4004 . Accessed 11 Apr 2019."},{"issue":"1","key":"9460_CR52","doi-asserted-by":"crossref","first-page":"27","DOI":"10.21248\/jlcl.32.2017.213","volume":"32","author":"TZ Osama Hamed","year":"2017","unstructured":"Osama Hamed, T. Z. (2017). A survey and comparative study of Arabic diacritization tools. JLCL, 32(1), 27\u201347.","journal-title":"JLCL"},{"key":"9460_CR53","unstructured":"Pasha, A., Al-Badrashiny, M., Diab, M., Kholy, A. E., Eskander, R., Habash, N., et al. (2014). MADAMIRA: A fast, comprehensive tool for morphological analysis and disambiguation of Arabic. In Proceedings of the 9th international conference on language resources and evaluation (LREC\u201914), Reykjavik, Iceland (pp. 1094\u20131101), http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/593_Paper.pdf . Accessed 11 Apr 2019."},{"key":"9460_CR54","unstructured":"Popescu, O., & Strapparava, C. (2015). SemEval 2015, Task 7: Diachronic text evaluation. In Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015), Denver, Colorado (pp. 870\u2013878), http:\/\/www.aclweb.org\/anthology\/S15-2147 . Accessed 11 Apr 2019."},{"key":"9460_CR55","unstructured":"Potthast, M., Stein, B., Barr\u00f3n-Cede\u00f1o, A., & Rosso, P. (2010). An evaluation framework for plagiarism detection. In C. R. Huang, D. Jurafsky (Eds.), Proceedings of the 23rd international conference on computational linguistics (COLING 2010) (pp. 997\u20131005). COLING 2010 Organizing Committee, Beijing, China."},{"issue":"1","key":"9460_CR56","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1109\/TASL.2010.2045240","volume":"19","author":"MA Rashwan","year":"2011","unstructured":"Rashwan, M. A., Al-Badrashiny, M. A., Attia, M., Abdou, S. M., & Rafea, A. (2011). A stochastic Arabic diacritizer based on a hybrid of factorized and unfactorized textual features. IEEE Transactions on Audio, Speech and Language Processing, 19(1), 166\u2013175. https:\/\/doi.org\/10.1109\/TASL.2010.2045240 .","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9460_CR57","unstructured":"Rehurek, R., & Sojka, P. (2010). Software framework for topic modelling with large corpora. In Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks (pp. 45\u201350). Valletta, Malta: ELRA."},{"issue":"S1","key":"9460_CR58","doi-asserted-by":"publisher","first-page":"S226","DOI":"10.1086\/693970","volume":"92","author":"M Romanov","year":"2017","unstructured":"Romanov, M. (2017). Algorithmic analysis of medieval Arabic biographical collections. Speculum, 92(S1), S226\u2013S246.","journal-title":"Speculum"},{"key":"9460_CR59","unstructured":"Romanov, M., Miller, M. T., & Savant, S. B. (2017\u2013ongoing). OpenITI\u2014machine-actionable scholarly corpus of premodern Islamicate texts, https:\/\/openiti.github.io . Accessed 11 Apr 2019."},{"key":"9460_CR60","unstructured":"Romanov, M. G. (2013). Computational reading of Arabic biographical collections with special reference to preaching in the sunni world (661\u20131300 CE). Ph.D. Thesis, University of Michigan, Ann Arbor, MI, USA"},{"key":"9460_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2017.07.003","author":"S Romeo","year":"2017","unstructured":"Romeo, S., Da San Martino, G., Belinkov, Y., Barr\u00f3n-Cede\u00f1o, A., Eldesouki, M., Darwish, K., et al. (2017). Language processing and learning models for community question answering in arabic. Information Processing & Management,. https:\/\/doi.org\/10.1016\/j.ipm.2017.07.003 .","journal-title":"Information Processing & Management"},{"key":"9460_CR62","unstructured":"Sagi, E., Kaufmann, S., & Clark, B. (2009). Semantic density analysis: Comparing word meaning across time and phonetic space. In Proceedings of the EACL 2009 workshop on GEMS: Geometrical models of natural language semantics (pp. 104\u2013111)."},{"key":"9460_CR63","unstructured":"Scherbinin, V., & Butakov, S. (2009). Using Microsoft SQL server platform for plagiarism detection. In B. Stein, P. Rosso, E. Stamatatos, M. Koppel, & E. Agirre (Eds.), SEPLN 2009 workshop on uncovering plagiarism, authorship, and social software misuse (PAN 2009) (Vol. 502). CEUR-WS.org, San Sebastian, Spain, http:\/\/ceur-ws.org\/Vol-502 . Accessed 11 Apr 2019."},{"key":"9460_CR64","unstructured":"Schneider, N., Mohit, B., Oflazer, K., & Smith, N. A. (2012). Coarse lexical semantic annotation with supersenses: An Arabic case study. In Proceedings of the 50th annual meeting of the association for computational linguistics: Short Papers, ACL\u201912 (Vol. 2 , pp. 253\u2013258). Stroudsburg, PA: Association for Computational Linguistics, http:\/\/dl.acm.org\/citation.cfm?id=2390665.2390726 . Accessed 11 Apr 2019."},{"issue":"1","key":"9460_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF02289451","volume":"31","author":"PH Sch\u00f6nemann","year":"1966","unstructured":"Sch\u00f6nemann, P. H. (1966). A generalized solution of the orthogonal procrustes problem. Psychometrika, 31(1), 1\u201310. https:\/\/doi.org\/10.1007\/BF02289451 .","journal-title":"Psychometrika"},{"key":"9460_CR66","unstructured":"Shmidman, A., Koppel, M., & Porat, E. (2016). Identification of parallel passages across a large hebrew\/aramaic corpus. arXiv preprint arXiv:1602.08715 ."},{"key":"9460_CR67","unstructured":"Shoufan, A., & Alameri, S. (2015). Natural language processing for dialectical Arabic: A survey. In Proceedings of the 2nd workshop on Arabic natural language processing, Beijing, China (pp. 36\u201348), http:\/\/www.aclweb.org\/anthology\/W15-3205 . Accessed 11 Apr 2019."},{"key":"9460_CR68","unstructured":"Smith, D. A., Cordell, R., Dillon, E. M., Stramp, N., & Wilkerson, J. (2014). Detecting and modeling local text reuse. In Proceedings of the 14th ACM\/IEEE-CS joint conference on digital libraries, JCDL\u201914, London, UK (pp. 183\u2013192), http:\/\/dl.acm.org\/citation.cfm?id=2740769.2740800 . Accessed 11 Apr 2019."},{"key":"9460_CR69","unstructured":"Stein, B., Rosso, P., Stamatatos, E., Koppel, M., & Agirre, E. (Eds.). (2009). SEPLN 2009 workshop on uncovering plagiarism, authorship, and social software misuse (PAN 2009) (Vol. 502). CEUR-WS.org, San Sebastian, Spain, http:\/\/ceur-ws.org\/Vol-502 . Accessed 11 Apr 2019."},{"key":"9460_CR70","doi-asserted-by":"publisher","unstructured":"Wijaya, D. T., & Yeniterzi, R. (2011). Understanding semantic change of words over centuries. In Proceedings of the 2011 international workshop on detecting and exploiting cultural diversity on the social web\u2014DETECT\u201911 (p.\u00a035), http:\/\/dl.acm.org\/citation.cfm?doid=2064448.2064475 . https:\/\/doi.org\/10.1145\/2064448.2064475 . Accessed 11 Apr 2019.","DOI":"10.1145\/2064448.2064475"},{"issue":"4","key":"9460_CR71","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1111\/ajps.12175","volume":"59","author":"J Wilkerson","year":"2015","unstructured":"Wilkerson, J., Smith, D., & Stramp, N. (2015). Tracing the flow of policy ideas in legislatures: A text reuse approach. American Journal of Political Science, 59(4), 943\u2013956. https:\/\/doi.org\/10.1111\/ajps.12175 .","journal-title":"American Journal of Political Science"},{"key":"9460_CR72","volume-title":"Middle Arabic and mixed Arabic: Diachrony and synchrony","year":"2012","unstructured":"Zack, E., & Schippers, A. (Eds.). (2012). Middle Arabic and mixed Arabic: Diachrony and synchrony. Leiden: Brill Academic Publishers."},{"key":"9460_CR73","unstructured":"Zaghouani, W. (2014). Critical survey of the freely available Arabic corpora. In Proceedings of the Workshop on Free\/Open-Source Arabic Corpora and Corpora Processing Tools."},{"key":"9460_CR74","unstructured":"Zem\u00e1nek, P., & Mili\u010dka, J. (2014a). Ranking search results for Arabic diachronic corpora. Google-like search engine for (non)linguists. In Proceedings of CITALA 2014 (5th International Conference on Arabic Language Processing). Association for Computational Linguistics."},{"key":"9460_CR75","doi-asserted-by":"crossref","unstructured":"Zem\u00e1nek, P., & Mili\u010dka, J. (2014b). Quotations, relevance and time depth: Medieval Arabic literature in grids and networks. In Proceedings of the 3rd workshop on computational linguistics for literature (CLFL), Gothenburg, Sweden (pp. 17\u201324), http:\/\/www.aclweb.org\/anthology\/W14-0903 . Accessed 11 Apr 2019.","DOI":"10.3115\/v1\/W14-0903"},{"key":"9460_CR76","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.dib.2017.01.011","volume":"11","author":"T Zerrouki","year":"2017","unstructured":"Zerrouki, T., & Balla, A. (2017). Tashkeela: Novel corpus of Arabic vocalized texts, data for auto-diacritization systems. Data in Brief, 11, 147\u2013151. https:\/\/doi.org\/10.1016\/j.dib.2017.01.011 .","journal-title":"Data in Brief"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-019-09460-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-019-09460-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-019-09460-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T18:02:56Z","timestamp":1694800976000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-019-09460-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,12]]},"references-count":77,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["9460"],"URL":"https:\/\/doi.org\/10.1007\/s10579-019-09460-w","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,12]]},"assertion":[{"value":"12 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}