{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:41Z","timestamp":1740123581457,"version":"3.37.3"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,11,28]],"date-time":"2016-11-28T00:00:00Z","timestamp":1480291200000},"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":["Artif Intell Rev"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s10462-016-9527-1","type":"journal-article","created":{"date-parts":[[2016,11,28]],"date-time":"2016-11-28T03:49:00Z","timestamp":1480304940000},"page":"339-373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A survey on Urdu and Urdu like language stemmers and stemming techniques"],"prefix":"10.1007","volume":"49","author":[{"given":"Abdul","family":"Jabbar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8464-2275","authenticated-orcid":false,"given":"Sajid","family":"Iqbal","sequence":"additional","affiliation":[]},{"given":"Muhammad Usman Ghani","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Shafiq","family":"Hussain","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,11,28]]},"reference":[{"issue":"4","key":"9527_CR1","first-page":"368","volume":"9","author":"M Ababneh","year":"2012","unstructured":"Ababneh M, Al-Shalabi R, Kanaan G, Al-Nobani A (2012) Building an effective rule-based light stemmer for Arabic language to improve search effectiveness. Int Arab J Inf Technol (IAJIT) 9(4):368\u2013372","journal-title":"Int Arab J Inf Technol (IAJIT)"},{"key":"9527_CR2","unstructured":"Abbas Q (2012) Building a hierarchical annotated corpus of urdu: the URDU. KON-TB treebank. In: International conference on intelligent text processing and computational linguistics. Berlin, pp 66\u201379"},{"key":"9527_CR3","unstructured":"Abu-Errub A, Odeh A, Shambour Q, Hassan OA-H (2014) Arabic roots extraction using morphological analysis. Int J Comput Sci 11:2"},{"key":"9527_CR4","doi-asserted-by":"crossref","unstructured":"Akram QA, Naseer A, Hussain S (2009) Assas-Band, an affix-exception-list based Urdu stemmer. In: Proceedings of the 7th workshop on Asian language resources. Association for Computational Linguistics, pp 40\u201346","DOI":"10.3115\/1690299.1690305"},{"key":"9527_CR5","doi-asserted-by":"crossref","unstructured":"Aljlayl M, Frieder O (2002) On Arabic search: improving the retrieval effectiveness via a light stemming approach. In: Proceedings of the eleventh international conference on Information and knowledge management. ACM, pp 340\u2013347","DOI":"10.1145\/584792.584848"},{"key":"9527_CR6","unstructured":"Al-Kabi M, Al-Mustafa R (2006) Arabic root based stemmer. In: Proceedings of the international Arab conference on information technology"},{"key":"9527_CR7","unstructured":"Al-Kabi M, Al-Shawakfa E, Alsmadi I (2013) The effect of stemming on Arabic text classification: an empirical study. Inf Retr Methods Multidiscip Appl 207\u2013225"},{"issue":"2","key":"9527_CR8","first-page":"94","volume":"27","author":"MN Al-Kabi","year":"2015","unstructured":"Al-Kabi MN, Kazakzeh SA, Ata BMA, Al-Rababah SA, Alsmadi IM (2015) A novel root based Arabic stemmer. J King Saud Univ Comput Inf Sci 27(2):94\u2013103","journal-title":"J King Saud Univ Comput Inf Sci"},{"issue":"6","key":"9527_CR9","first-page":"702","volume":"9","author":"A Al-Omari","year":"2014","unstructured":"Al-Omari A, Abuata B (2014) Arabic light stemmer (ARS). J Eng Sci Technol 9(6):702\u2013717","journal-title":"J Eng Sci Technol"},{"key":"9527_CR10","unstructured":"Al-Shammari ET (2013) Lemmatizing, stemming, and query expansion method and system. U.S. Patent No. 8,473,279. 25 Jun 2013"},{"key":"9527_CR11","doi-asserted-by":"crossref","unstructured":"Al-Shammari ET, Lin J (2008) Towards an error-free Arabic stemming. In: Proceedings of the 2nd ACM workshop on improving non English web searching. ACM, pp 9\u201316","DOI":"10.1145\/1460027.1460030"},{"issue":"3","key":"9527_CR12","doi-asserted-by":"crossref","first-page":"262","DOI":"10.7763\/LNSE.2014.V2.134","volume":"2","author":"V Balakrishnan","year":"2014","unstructured":"Balakrishnan V, Lloyd-Yemoh E (2014) Stemming and lemmatization: a comparison of retrieval performances. Lect Notes Softw Eng 2(3):262\u2013267","journal-title":"Lect Notes Softw Eng"},{"issue":"2","key":"9527_CR13","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/MCI.2014.2307227","volume":"9","author":"E Cambria","year":"2014","unstructured":"Cambria E, White B (2014) Jumping NLP curves: a review of natural language processing research. IEEE Comput Intell Mag 9(2):48\u201357","journal-title":"IEEE Comput Intell Mag"},{"issue":"1","key":"9527_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2071389.2071390","volume":"44","author":"C Carpineto","year":"2012","unstructured":"Carpineto C, Romano G (2012) A survey of automatic query expansion in information retrieval. ACM Comput Surv (CSUR) 44(1):1","journal-title":"ACM Comput Surv (CSUR)"},{"key":"9527_CR15","unstructured":"Chen A, Gey FC (2002) Building an Arabic stemmer for information retrieval. In: TREC, pp 631\u2013639"},{"issue":"3","key":"9527_CR16","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/101306.101310","volume":"24","author":"DP Chris","year":"1990","unstructured":"Chris DP (1990) Another stemmer. ACM. SIGIR Forum 24(3):56\u201361","journal-title":"SIGIR Forum"},{"key":"9527_CR17","doi-asserted-by":"crossref","unstructured":"Dahab MY, Al-Mutawa R (2015) A comparative study on Arabic stemmers. Change 125(8):","DOI":"10.5120\/ijca2015906129"},{"issue":"2","key":"9527_CR18","first-page":"89","volume":"3","author":"MH Dianati","year":"2014","unstructured":"Dianati MH, Hadi SM, Rasekh AH, Fakhrahmad SM, Taghi-Zadeh H (2014) Words stemming based on structural and semantic similarity. Comput Eng Appl J 3(2):89\u201399","journal-title":"Comput Eng Appl J"},{"key":"9527_CR19","doi-asserted-by":"crossref","unstructured":"Ebrahim S, Hegazy D, Mostafa MG, El-Beltagy SR (2015) English\u2013Arabic statistical machine translation: state of the art. In: International conference on intelligent text processing and computational linguistics. Springer International Publishing, pp 520\u2013533","DOI":"10.1007\/978-3-319-18111-0_39"},{"key":"9527_CR20","doi-asserted-by":"crossref","unstructured":"El-Beltagy Samhaa R, Rafea Ahmed (2011) An accuracy-enhanced light stemmer for arabic text. ACM Trans Speech Lang Process (TSLP) 7(2):2","DOI":"10.1145\/1921656.1921657"},{"issue":"3","key":"9527_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijnlc.2015.4301","volume":"4","author":"M El-Defrawy","year":"2015","unstructured":"El-Defrawy M, El-Sonbaty Y, Belal NA (2015) Cbas: context based arabic stemmer. Int J Nat Lang Comput (IJNLC) 4(3):1\u201312","journal-title":"Int J Nat Lang Comput (IJNLC)"},{"key":"9527_CR22","unstructured":"El Kholy A et\u00a0al (2013) Selective combination of pivot and direct statistical machine translation models.\u00a0In: Proceedings of the 6th international joint conference on natural language processing"},{"key":"9527_CR23","doi-asserted-by":"crossref","unstructured":"Estahbanati A, Javidan R, Dezfooli MA (2011) Implementation of a new method for stemming in Persian language. In: Proceedings of the international conference on web intelligence, mining and semantics. ACM, p 63","DOI":"10.1145\/1988688.1988761"},{"key":"9527_CR24","unstructured":"Frakes WB (1992) Information retrieval: data structures and algorithms, Chapter 8. http:\/\/orion.lcg.ufrj.br\/Dr.Dobbs\/books\/book5\/chap08.htm . Retrieved 1 Oct 2015"},{"key":"9527_CR25","doi-asserted-by":"crossref","unstructured":"Ghwanmeh S, Kanaan G, Al-Shalabi R, Rabab\u2019ah S (2009) Enhanced algorithm for extracting the root of Arabic words. In: Sixth international conference on computer graphics, imaging and visualization, 2009. CGIV\u201909. IEEE, pp 388\u2013391","DOI":"10.1109\/CGIV.2009.10"},{"key":"9527_CR26","unstructured":"Goweder A, Alhami H, Rashed T, Al-Musrati A (2008) A hybrid method for stemming Arabic text. J Comput Sci. http:\/\/eref.uqu.edu.sa\/files\/eref2\/folder6\/f181.pdf"},{"key":"9527_CR27","doi-asserted-by":"crossref","unstructured":"Gupta V, Joshi N, Mathur I (2013) Rule based stemmer in Urdu. In: 2013 4th international conference on computer and communication technology (ICCCT). IEEE, pp 129\u2013132","DOI":"10.1109\/ICCCT.2013.6749615"},{"key":"9527_CR28","unstructured":"Gupta V, Joshi N, Mathur I (2015) Design and development of rule based inflectional and derivational Urdu stemmer \u2018Usal\u2019. In: 2015 international conference on futuristic trends on computational analysis and knowledge management (ABLAZE). IEEE, pp 7\u201312"},{"key":"9527_CR29","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/978-1-4020-6046-5_14","volume-title":"Arabic computational morphology","author":"N Habash","year":"2007","unstructured":"Habash N (2007) Arabic morphological representations for machine translation. Arabic computational morphology. Springer, Netherlands, pp 263\u2013285"},{"key":"9527_CR30","doi-asserted-by":"crossref","unstructured":"Hadni M, Lachkar A, Alaoui OS (2012) A new and efficient stemming technique for Arabic Text Categorization.\u00a0In: 2012 international conference on multimedia computing and systems (ICMCS). IEEE","DOI":"10.1109\/ICMCS.2012.6320308"},{"issue":"4","key":"9527_CR31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2013.3401","volume":"3","author":"M Hadni","year":"2013","unstructured":"Hadni M, Ouatik SA, Lachkar A (2013) Effective Arabic stemmer based hybrid approach for Arabic text categorization. Int J Data Min Knowl Manag Process (IJDKP) 3(4):1\u201314","journal-title":"Int J Data Min Knowl Manag Process (IJDKP)"},{"key":"9527_CR32","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-642-31600-5_5","volume-title":"Advances in computing and information technology","author":"MS Husain","year":"2013","unstructured":"Husain MS, Ahamad F, Khalid S (2013) A language independent approach to develop Urdu stemmer. Advances in computing and information technology. Springer, Berlin, pp 45\u201353"},{"key":"9527_CR33","unstructured":"Hussain S (2008) Resources for Urdu language processing. In: IJCNLP, pp 99\u2013100"},{"key":"9527_CR34","unstructured":"Hussain S, Afzal M, (2001) Urdu computing standards: Urdu zabta takhti (uzt) 1.01. In: Multi topic conference, (2001) IEEE INMIC 2001, Technology for the 21st century. Proceedings, IEEE International, IEEE"},{"key":"9527_CR35","unstructured":"Khan S, Anwar W, Bajwa U, Wang X (2015) Template based affix stemmer for a morphologically rich language. Int Arab J Inf Technol 12(2):146\u2013154"},{"key":"9527_CR36","unstructured":"Khan SA, Anwar W, Ijaz BU, Wang X (2012) A light weight stemmer for Urdu language: a scarce resourced language. In: 24th international conference on computational linguistics, p 69"},{"issue":"11","key":"9527_CR37","doi-asserted-by":"crossref","first-page":"2360","DOI":"10.4304\/tpls.4.11.2360-2365","volume":"4","author":"AA Khansir","year":"2014","unstructured":"Khansir AA, Mozafari N (2014) The impact of Persian language on Indian languages. Theory Pract Lang Stud 4(11):2360\u20132365","journal-title":"Theory Pract Lang Stud"},{"key":"9527_CR38","unstructured":"Khoja S, Garside R (1999) Stemming Arabic text 1999. http:\/\/zeus.cs.pacificu.edu\/shereen\/research.htm#stemming . Accessed 27 Dec 2015"},{"key":"9527_CR39","doi-asserted-by":"crossref","unstructured":"Korenius T et\u00a0al (2004) Stemming and lemmatization in the clustering of finnish text documents. In: Proceedings of the thirteenth ACM international conference on Information and knowledge management. ACM","DOI":"10.1145\/1031171.1031285"},{"issue":"3","key":"9527_CR40","first-page":"349","volume":"2","author":"RV Lakshmi","year":"2014","unstructured":"Lakshmi RV, Kumar SBR (2014) Literature review: stemming algorithms for Indian and Non-Indian languages. Int J Adv Res Comput Sci Technol 2(3):349\u2013352","journal-title":"Int J Adv Res Comput Sci Technol"},{"key":"9527_CR41","doi-asserted-by":"crossref","unstructured":"Larkey LS, Ballesteros L, Connell ME (2002) Improving stemming for Arabic information retrieval: light stemming and co-occurrence analysis. In: Proceedings of the 25th annual international ACM SIGIR conference on research and development in information retrieval. ACM, pp 275\u2013282","DOI":"10.1145\/564376.564425"},{"key":"9527_CR42","unstructured":"Lehal RKVGGS (2012) Rule based Urdu stemmer. In: 24th international conference on computational linguistics, p 267"},{"key":"9527_CR43","volume-title":"Development of a stemming algorithm","author":"JB Lovins","year":"1968","unstructured":"Lovins JB (1968) Development of a stemming algorithm. Electronic Systems Laboratory, MIT Information Processing Group, Cambridge"},{"key":"9527_CR44","unstructured":"Madnani N, Tetreault J, Chodorow M (2012) Re-examining machine translation metrics for paraphrase identification.\u00a0In: Proceedings of the 2012 conference of the North American chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics"},{"key":"9527_CR45","doi-asserted-by":"crossref","unstructured":"Mahmoodi M, Varnamkhasti MM (2014) Design a Persian automated plagiarism detector (AMZPPD).\u00a0arXiv preprint arXiv:1403.1618","DOI":"10.14445\/22315381\/IJETT-V8P280"},{"issue":"4","key":"9527_CR46","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1145\/1281485.1281489","volume":"25","author":"P Majumder","year":"2007","unstructured":"Majumder P, Mandar M, Swapan KP, Kole G, Mitra P, Datta K (2007) YASS: yet another suffix stripper. ACM Trans Inf Syst (TOIS) 25(4):18","journal-title":"ACM Trans Inf Syst (TOIS)"},{"key":"9527_CR47","doi-asserted-by":"crossref","unstructured":"Melucci M, Orio N (2003) A novel method for stemmer generation based on hidden Markov models. In: Proceedings of the twelfth international conference on information and knowledge management. ACM, pp 131\u2013138","DOI":"10.1145\/956863.956889"},{"key":"9527_CR48","unstructured":"Moghadam FM, Keyvanpour M (2015) Comparative study of various Persian stemmers in the field of information retrieval. J Inf Process Syst 11(3):450\u2013464"},{"key":"9527_CR49","doi-asserted-by":"crossref","unstructured":"Mokhtaripour A, Jahanpour S (2006) Introduction to a new Farsi stemmer. In: Proceedings of the 15th ACM international conference on information and knowledge management. ACM, pp 826\u2013827","DOI":"10.1145\/1183614.1183750"},{"key":"9527_CR50","unstructured":"Mubashir Ali SK, Saleemi MH (2014) A novel stemming approach for Urdu language. J Appl Environ Biol Sci 4(7S)436\u2013443. ISSN: 2090\u20134274. www.textroad.com"},{"key":"9527_CR51","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1007\/11575832_23","volume-title":"International symposium on string processing and information retrieval","author":"AFA Nwesri","year":"2005","unstructured":"Nwesri AFA, Tahaghoghi SMM, Scholer F (2005) Stemming Arabic conjunctions and prepositions. International symposium on string processing and information retrieval. Springer, Berlin, pp 206\u2013217"},{"key":"9527_CR52","first-page":"42","volume-title":"Proceedings of the 17th annual international ACM SIGIR conference on research and development in information retrieval","author":"CD Paice","year":"1994","unstructured":"Paice CD (1994) An evaluation method for stemming algorithms. Proceedings of the 17th annual international ACM SIGIR conference on research and development in information retrieval. Springer, New York, pp 42\u201350"},{"issue":"2","key":"9527_CR53","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. Synth Lect Hum Lang Technol 5(2):1\u2013157","journal-title":"Synth Lect Hum Lang Technol"},{"issue":"3","key":"9527_CR54","first-page":"130","volume":"14","author":"MF Porter","year":"1980","unstructured":"Porter MF (1980) An algorithm for suffix stripping. Program 14(3):130\u2013137","journal-title":"An algorithm for suffix stripping. Program"},{"key":"9527_CR55","unstructured":"Rahimi A (2015) A new hybrid stemming algorithm for Persian. arXiv preprint arXiv:1507.03077"},{"key":"9527_CR56","doi-asserted-by":"crossref","unstructured":"Rahimtoroghi E, Faili H, Shakery A (2010) A structural rule-based stemmer for Persian. In: 2010 5th international symposium on telecommunications (IST). IEEE, pp 574\u2013578","DOI":"10.1109\/ISTEL.2010.5734090"},{"key":"9527_CR57","doi-asserted-by":"crossref","unstructured":"Rashidi A, Lighvan MZ (2014) HPS: a hierarchical Persian stemming method. arXiv preprint arXiv:1403.2837","DOI":"10.5121\/ijnlc.2014.3102"},{"key":"9527_CR58","doi-asserted-by":"crossref","unstructured":"Sarabi Z, Hamidreza M, Mojgan F (2013) Parsi Pardaz: Persian Language Processing Toolkit.\u00a0In: 2013 3rd international conference on computer and knowledge engineering (ICCKE). IEEE","DOI":"10.1109\/ICCKE.2013.6682862"},{"key":"9527_CR59","first-page":"303","volume-title":"International conference on application of natural language to information systems","author":"M Saraee","year":"2013","unstructured":"Saraee M, Bagheri A (2013) Feature selection methods in Persian sentiment analysis. International conference on application of natural language to information systems. Springer, Berlin, pp 303\u2013308"},{"key":"9527_CR60","doi-asserted-by":"crossref","unstructured":"Seo Y-W, Ankolekar A, Sycara K (2004) Feature selection for extracting semantically rich words. No. CMU-RI-TR-04\u201318. Robotics Inst., Carnegie-Mellon Univ., Pittsburgh","DOI":"10.21236\/ADA597268"},{"key":"9527_CR61","unstructured":"Sharifloo AA, Shamsfard M (2008) A bottom up approach to Persian stemming. In: IJCNLP, pp 583\u2013588"},{"issue":"2","key":"9527_CR62","first-page":"265","volume":"4","author":"SR Sirsat","year":"2013","unstructured":"Sirsat SR, Chavan V, Mahalle HS (2013) Strength and accuracy analysis of affix removal stemming algorithms. Int J Comput Sci Inf Technol 4(2):265\u2013269","journal-title":"Int J Comput Sci Inf Technol"},{"key":"9527_CR63","doi-asserted-by":"crossref","unstructured":"Taghi-Zadeh H, Hadi SM, Diyanati MH, Rasekh AH (2015) A new hybrid stemming method for Persian language. Digital Scholarship in the Humanities: fqv053","DOI":"10.1093\/llc\/fqv053"},{"key":"9527_CR64","doi-asserted-by":"crossref","unstructured":"Taghva K, Beckley R, Sadeh M (2005a) A stemming algorithm for the farsi language. In: Null. IEEE, pp 158\u2013162","DOI":"10.1109\/ITCC.2005.40"},{"key":"9527_CR65","doi-asserted-by":"crossref","unstructured":"Taghva K, Elkhoury R, Coombs J (2005b) Arabic stemming without a root dictionary. In: Innull. IEEE, pp 152\u2013157","DOI":"10.1109\/ITCC.2005.90"},{"issue":"1","key":"9527_CR66","first-page":"1","volume":"5","author":"N Tahir","year":"2014","unstructured":"Tahir N (2014) Impact of Arabic language on Urdu language. VFAST Trans Islam Res 5(1):1\u201313","journal-title":"VFAST Trans Islam Res"},{"key":"9527_CR67","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/3-540-36087-5_57","volume-title":"EurAsia-ICT 2002: information and communication technology","author":"M Tashakori","year":"2002","unstructured":"Tashakori M, Meybodi M, Oroumchian F (2002) Bon: the Persian stemmer. EurAsia-ICT 2002: information and communication technology. Springer, Berlin, pp 487\u2013494"},{"issue":"3","key":"9527_CR68","first-page":"1022","volume":"50","author":"M Zughoul","year":"2005","unstructured":"Zughoul M, Abu-Alshaar A (2005) English\/Arabic\/English machine translation: a historical perspective. Transl J 50(3):1022\u20131041","journal-title":"Transl J"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-016-9527-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9527-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9527-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T20:57:52Z","timestamp":1568581072000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-016-9527-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,28]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["9527"],"URL":"https:\/\/doi.org\/10.1007\/s10462-016-9527-1","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"type":"print","value":"0269-2821"},{"type":"electronic","value":"1573-7462"}],"subject":[],"published":{"date-parts":[[2016,11,28]]}}}