{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T21:54:36Z","timestamp":1781214876596,"version":"3.54.1"},"reference-count":150,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,8,1]],"date-time":"2016-08-01T00:00:00Z","timestamp":1470009600000},"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":[[2017,8]]},"DOI":"10.1007\/s10462-016-9498-2","type":"journal-article","created":{"date-parts":[[2016,8,1]],"date-time":"2016-08-01T16:44:00Z","timestamp":1470069840000},"page":"157-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["A systematic review of text stemming techniques"],"prefix":"10.1007","volume":"48","author":[{"given":"Jasmeet","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishal","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,8,1]]},"reference":[{"key":"9498_CR1","doi-asserted-by":"crossref","unstructured":"Adam G, Asimakis K, Bouras C, Poulopoulos V (2010) An efficient mechanism for stemming and tagging: the case of greek language. In: Proceedings of the 14th international conference on knowledge-based and intelligent information and engineering systems, pp 389\u2013397","DOI":"10.1007\/978-3-642-15393-8_44"},{"key":"9498_CR2","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1002\/(SICI)1097-4571(199612)47:12<909::AID-ASI4>3.0.CO;2-6","volume":"47","author":"F Ahmad","year":"1996","unstructured":"Ahmad F, Yusoff M, Sembok T (1996) Experiments with a stemming algorithm for Malay words. J Am Soc Inf Sci 47:909\u2013918","journal-title":"J Am Soc Inf Sci"},{"key":"9498_CR3","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1002\/asi.21063","volume":"60","author":"F Ahmed","year":"2009","unstructured":"Ahmed F, N\u00fcrnberger A (2009) Evaluation of n-gram conflation approaches for Arabic text retrieval. J Am Soc Inf Sci Technol 60:1448\u20131465","journal-title":"J Am Soc Inf Sci Technol"},{"key":"9498_CR4","doi-asserted-by":"crossref","unstructured":"Akram Q-A, Naseer A, Hussain S (2009) Assas-band, an affix-exception-list based Urdu stemmer. In: Proceedings of the 7th workshop on Asian language resources, pp 40\u201346","DOI":"10.3115\/1690299.1690305"},{"key":"9498_CR5","doi-asserted-by":"crossref","unstructured":"Aljlayl M, Frieder O (2002) On Arabic search: improving the retrieval effectiveness via a light stemming approach. In: ACM eleventh conference on information and knowledge management, pp 340\u2013347","DOI":"10.1145\/584792.584848"},{"key":"9498_CR6","doi-asserted-by":"crossref","unstructured":"Al-Kabi M (2013) Towards improving Khoja rule-based Arabic stemmer. In: IEEE Jordan conference on applied electrical engineering and computing technologies (AEECT), pp 1\u20136","DOI":"10.1109\/AEECT.2013.6716437"},{"key":"9498_CR7","doi-asserted-by":"crossref","first-page":"38","DOI":"10.3923\/itj.2005.38.43","volume":"4","author":"R Alshalabi","year":"2005","unstructured":"Alshalabi R (2005) Pattern-based stemmer for finding Arabic roots. Inf Technol J 4:38\u201343","journal-title":"Inf Technol J"},{"key":"9498_CR8","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3923\/itj.2005.55.62","volume":"4","author":"R Al-Shalabi","year":"2005","unstructured":"Al-Shalabi R, Kannan G, Hilat I et al (2005) Experiments with the successor variety algorithm using the cutoff and entropy methods. Inf Technol J 4:55\u201362","journal-title":"Inf Technol J"},{"key":"9498_CR9","doi-asserted-by":"crossref","unstructured":"Al-shammari E, Lin J (2008) Towards an error-free Arabic stemming. In: Proceedings of the 2nd ACM workshop on improving non English web searching, iNEWS\u201908, pp 9\u201316","DOI":"10.1145\/1460027.1460030"},{"key":"9498_CR10","doi-asserted-by":"crossref","unstructured":"Alvares R, Garcia A, Ferraz I (2005) STEMBR: a stemming algorithm for the Brazilian Portuguese language. In: Proceedings of 12th Portuguese conference on artificial intelligence, EPIA 2005, pp 693\u2013701","DOI":"10.1007\/11595014_67"},{"key":"9498_CR11","doi-asserted-by":"crossref","unstructured":"Al-Zyoud A, Al-Rabayah W (2015) Arabic stemming techniques: comparisons and new vision. In: Proceedings of the 8th IEEE GCC conference and exhibition, pp 1\u20136","DOI":"10.1109\/IEEEGCC.2015.7060020"},{"key":"9498_CR12","doi-asserted-by":"crossref","unstructured":"Amati G (2006) Frequentist and bayesian approach to information retrieval. In: Advances in information retrieval. Springer, pp 13\u201324","DOI":"10.1007\/11735106_3"},{"key":"9498_CR13","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1145\/582415.582416","volume":"20","author":"G Amati","year":"2002","unstructured":"Amati G, Van Rijsbergen CJ (2002) Probabilistic models of information retrieval based on measuring the divergence from randomness. ACM Trans Inf Syst 20:357\u2013389","journal-title":"ACM Trans Inf Syst"},{"key":"9498_CR14","unstructured":"Apache lucene. http:\/\/lucene.apache.org"},{"key":"9498_CR15","unstructured":"Baayen RH, Piepenbrock R, van H R (1993) The CELEX lexical data base (CD-ROM). Linguistic data consortium. University of Pennsylvania, Philadelphia"},{"key":"9498_CR16","doi-asserted-by":"crossref","unstructured":"Bacchin M, Ferro N, Melucci M (2002) The effiectiveness of a graph-based algorithm for stemming. In: Digital libraries: people, knowledge, and technology. Springer, pp 117\u2013128","DOI":"10.1007\/3-540-36227-4_12"},{"key":"9498_CR17","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.ipm.2004.04.006","volume":"41","author":"M Bacchin","year":"2005","unstructured":"Bacchin M, Ferro N, Melucci M (2005) A probabilistic model for stemmer generation. Inf Process Manag 41:121\u2013137","journal-title":"Inf Process Manag"},{"key":"9498_CR18","volume-title":"Modern information retrieval: the concepts and technology behind search","author":"R Baeza-Yates","year":"2011","unstructured":"Baeza-Yates R, Ribeiro-Neto B (2011) Modern information retrieval: the concepts and technology behind search, 2nd edn. ACM Press, Los Angeles","edition":"2"},{"key":"9498_CR19","doi-asserted-by":"crossref","unstructured":"Baroni M, Matiasek J, Trost H (2002) Unsupervised discovery of morphologically related words based on orthographic and semantic similarity. In: Workshop on morphological and phonological learning (MPL\u201902), pp 48\u201357","DOI":"10.3115\/1118647.1118653"},{"key":"9498_CR20","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1109\/TSMCB.2006.885307","volume":"37","author":"NL Bhamidipati","year":"2007","unstructured":"Bhamidipati NL, Pal SK (2007) Stemming via distribution-based word segregation for classification and retrieval. IEEE Trans Syst Man Cybern B Cybern 37:350\u2013360","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"9498_CR21","unstructured":"Bhattacharya S, Chhoudhury M, Sarkar S, Basu A (2005) Inflectional morphology synthesis for Bengali noun, pronoun and verb systems. In: Proceedings of the national conference on computer processing of Bangla, pp 34\u201343"},{"key":"9498_CR22","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-3-319-01778-5_19","volume":"235","author":"M Biba","year":"2014","unstructured":"Biba M, Gjatu E (2014) Boosting text classification through stemming of composite words. Recent Adv Intell Inform 235:185\u2013194","journal-title":"Recent Adv Intell Inform"},{"key":"9498_CR23","unstructured":"Bisazza A, Federico M (2009) Morphological pre-processing for Turkish to English statistical machine translation. In: International workshop on spoken language translation, pp 129\u2013135"},{"key":"9498_CR24","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1023\/B:INRT.0000011208.60754.a1","volume":"7","author":"M Braschler","year":"2004","unstructured":"Braschler M, RippLinger B (2004) How effective is stemming and decompounding for German text retrieval? Inf Retr Boston 7:291\u2013316","journal-title":"Inf Retr Boston"},{"key":"9498_CR25","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.ipm.2014.08.006","volume":"51","author":"T Brychc\u00edn","year":"2015","unstructured":"Brychc\u00edn T, Konop\u00edk M (2015) HPS: high precision stemmer. Inf Process Manag 51:68\u201391","journal-title":"Inf Process Manag"},{"key":"9498_CR26","unstructured":"Carlberger J, Dalianis H, Hassel M, Knutsson O (2001) Improving precision in information retrieval for Swedish using stemming. In: Proceedings of 13th Nordic conference on computational linguistics (NODALIDA \u201901)"},{"key":"9498_CR27","doi-asserted-by":"crossref","unstructured":"Chan E (2006) Learning probabilistic paradigms for morphology in a latent class model. In: Proceedings of the eighth meeting of the ACL special interest group on computational phonology and morphology, pp 69\u201378","DOI":"10.3115\/1622165.1622174"},{"key":"9498_CR28","first-page":"1","volume":"1","author":"S Chaupattnaik","year":"2012","unstructured":"Chaupattnaik S, Nanda S, Mohanty S (2012) A suffix stripping algorithm for Odia stemmer. Int J Comput Linguist Nat Lang Process 1:1\u20135","journal-title":"Int J Comput Linguist Nat Lang Process"},{"key":"9498_CR29","unstructured":"Chen A, Gey F (2002) Building an Arabic stemmer for information retrieval. In: Proceedings of the text retrieval conference (TREC\u201902), pp 631\u2013639"},{"key":"9498_CR30","unstructured":"Cilden E (2006) Stemming Turkish words using snowball. http:\/\/snowball.tartarus.org\/algorithms\/turkish\/stemmer.html"},{"key":"9498_CR31","unstructured":"Darwish K, Oard D (2002) CLIR experiments at Maryland for TREC-2002: Evidence combination for Arabic-English retrieval. In: Proceedings of the text retrieval conference (TREC\u201902), pp 703\u2013710"},{"key":"9498_CR32","unstructured":"Das A, Bandyopadhyay S (2010) Morphological stemming cluster identification for Bangla. In: Knowledge sharing event-I: task 3: morphological analyzers and generators, Mysore"},{"key":"9498_CR33","unstructured":"Dasgupta S, Khan M (2004) Feature unification for morphological parsing in Bangla. In: Proceedings of the 7th international conference on computer and information technology"},{"key":"9498_CR34","first-page":"33","volume":"2","author":"JL Dawson","year":"1974","unstructured":"Dawson JL (1974) Suffix removal for word conflation. Bull Assoc Lit Linguist Comput 2:33\u201346","journal-title":"Bull Assoc Lit Linguist Comput"},{"key":"9498_CR35","doi-asserted-by":"crossref","unstructured":"Deepamala N, Kumar P (2015) Kannada stemmer and its effect on Kannada documents classification. In: Proceedings of the international conference on computational intelligence in data mining, pp 75\u201386","DOI":"10.1007\/978-81-322-2202-6_7"},{"key":"9498_CR36","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.ipm.2009.06.001","volume":"45","author":"L Dolamic","year":"2009","unstructured":"Dolamic L, Savoy J (2009a) Indexing and stemming approaches for the Czech language. Inf Process Manag 45:714\u2013720","journal-title":"Inf Process Manag"},{"key":"9498_CR37","doi-asserted-by":"crossref","first-page":"2540","DOI":"10.1002\/asi.21191","volume":"60","author":"L Dolamic","year":"2009","unstructured":"Dolamic L, Savoy J (2009b) Indexing and searching strategies for the Russian language. J Am Soc Inf Sci Technol 60:2540\u20132547","journal-title":"J Am Soc Inf Sci Technol"},{"key":"9498_CR38","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/1838745.1838748","volume":"9","author":"L Dolamic","year":"2010","unstructured":"Dolamic L, Savoy J (2010) Comparative study of indexing and search strategies for the Hindi, Marathi, and Bengali languages. ACM Trans Asian Lang Inf Process 9:11","journal-title":"ACM Trans Asian Lang Inf Process"},{"key":"9498_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1921656.1921657","volume":"7","author":"S El-Beltagy","year":"2011","unstructured":"El-Beltagy S, Rafea A (2011) An accuracy-enhanced light stemmer for Arabic text. ACM Trans Speech Lang Process 7:1\u201322","journal-title":"ACM Trans Speech Lang Process"},{"key":"9498_CR40","doi-asserted-by":"crossref","unstructured":"Elrajubi O (2013) An improved Arabic light stemmer. In: 3rd International conference on research and innovation in information systems (ICRIIS\u201913), pp 33\u201338","DOI":"10.1109\/ICRIIS.2013.6716682"},{"key":"9498_CR41","unstructured":"Eryi\u011fit G, Adal\u0131 E (2004) An affix stripping morphological analyzer for Turkish. In: Proceedings of the IASTED international conference artificial intelligence and applications"},{"key":"9498_CR42","doi-asserted-by":"crossref","unstructured":"Fareed NS, Mousa HM, Elsisi AB (2013) Enhanced semantic Arabic Question answering system based on Khoja stemmer and AWN. In: 9th international computer engineering conference (ICENCO). IEEE, Giza, pp 85\u201391","DOI":"10.1109\/ICENCO.2013.6736481"},{"key":"9498_CR43","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez A, D\u00edaz J, Guti\u00e9rrez Y (2011) An unsupervised method to improve Spanish stemmer. In: Natural language processing and information systems. Springer, pp 221\u2013224","DOI":"10.1007\/978-3-642-22327-3_24"},{"key":"9498_CR44","unstructured":"Figuerola C, Gomez R, Rodriguez A, Berrocal J (2001) Stemming in Spanish: a first approach to its impact on information retrieval. In: Working notes of CLEF 2001 workshop. Darmstadt, Germany, pp 197\u2013202"},{"key":"9498_CR45","unstructured":"Frakes WB (1992) Stemming algorithms. In: Frakes WB, Baeza-Yates R (eds) Information retrieval: data structures and algorithms. Prentice-Hall, Upper Saddle River, New Jersey, pp 131\u2013160"},{"key":"9498_CR46","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1145\/945546.945548","volume":"37","author":"WB Frakes","year":"2003","unstructured":"Frakes WB, Fox CJ (2003) Strength and similarity of affix removal stemming algorithms. ACM SIGIR Forum 37:26\u201330","journal-title":"ACM SIGIR Forum"},{"key":"9498_CR47","doi-asserted-by":"crossref","unstructured":"Froud H, Benslimane R, Lachkar A, Ouatik SA (2010) Stemming and similarity measures for Arabic documents clustering. In: 5th International symposium on communications and mobile network (ISVC), pp 1\u20134","DOI":"10.1109\/ISVC.2010.5656417"},{"key":"9498_CR48","unstructured":"Ganguly D, Leveling J, Jones G (2012) DCU@FIRE-2012: rule-based stemmers for Bengali and Hindi. In: Fourth workshop of the forum for information retrieval evaluation (FIRE 2012)"},{"key":"9498_CR49","first-page":"104","volume":"45","author":"T Gaustad","year":"2002","unstructured":"Gaustad T, Bouma G, Groningen R (2002) Accurate stemming of Dutch for text classification. Lang Comput 45:104\u2013117","journal-title":"Lang Comput"},{"key":"9498_CR50","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1162\/089120101750300490","volume":"27","author":"J Goldsmith","year":"2001","unstructured":"Goldsmith J (2001) Unsupervised learning of the morphology of a natural language. J Comput Linguist 27:153\u2013198","journal-title":"J Comput Linguist"},{"key":"9498_CR51","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1017\/S1351324905004055","volume":"12","author":"J Goldsmith","year":"2006","unstructured":"Goldsmith J (2006) An algorithm for the unsupervised learning of morphology. Nat Lang Eng 12:353\u2013371","journal-title":"Nat Lang Eng"},{"key":"9498_CR52","first-page":"62","volume":"4","author":"V Gupta","year":"2014","unstructured":"Gupta V (2014) Hindi rule based stemmer for nouns. Int J Adv Res Comput Sci Softw Eng 4:62\u201365","journal-title":"Int J Adv Res Comput Sci Softw Eng"},{"key":"9498_CR53","unstructured":"Gupta V, Lehal GS (2011) Punjabi language stemmer for nouns and proper names. In: Proceedings of the 2nd workshop on south and southeast Asian natural language processing (WSSANLP), pp 35\u201339"},{"key":"9498_CR54","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/0020-0271(74)90044-8","volume":"10","author":"MA Hafer","year":"1974","unstructured":"Hafer MA, Weiss SF (1974) Word segmentation by letter successor varieties. Inf Storage Retr 10:371\u2013385","journal-title":"Inf Storage Retr"},{"key":"9498_CR55","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1162\/COLI_a_00050","volume":"37","author":"H Hammarstr\u00f6m","year":"2011","unstructured":"Hammarstr\u00f6m H, Borin L (2011) Unsupervised learning of morphology. Comput Linguist 37:309\u2013350","journal-title":"Comput Linguist"},{"key":"9498_CR56","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1002\/(SICI)1097-4571(199101)42:1<7::AID-ASI2>3.0.CO;2-P","volume":"42","author":"D Harman","year":"1991","unstructured":"Harman D (1991) How effective is suffixing? J Am Soc Inf Sci 42:7\u201315","journal-title":"J Am Soc Inf Sci"},{"key":"9498_CR57","first-page":"265","volume":"3","author":"H Harmanani","year":"2006","unstructured":"Harmanani H, Keirouz W, Raheel S (2006) A rule-based extensible stemmer for information retrieval with application to Arabic. Int Arab J Inf Technol 3:265\u2013272","journal-title":"Int Arab J Inf Technol"},{"key":"9498_CR58","doi-asserted-by":"crossref","unstructured":"Hegde Y, Kadambe S, Naduthota P (2013) Suffix stripping algorithm for Kannada information retrieval. In: International conference on advances in computing, communications and informatics (ICACCI), pp 527\u2013533","DOI":"10.1109\/ICACCI.2013.6637227"},{"key":"9498_CR59","unstructured":"Hiemstra D (2001) Using language models for information retrieval. Taaluitgeverij Neslia Paniculata"},{"key":"9498_CR60","doi-asserted-by":"crossref","unstructured":"Honrado A, Leon R, O\u2019Dennol R, Sinclair D (2000) A word stemming algorithm for the Spanish language. In: Proceedings of the 7th international symposium on string processing and information retrieval, pp 139\u2013145","DOI":"10.1109\/SPIRE.2000.878189"},{"key":"9498_CR61","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139166003","volume-title":"English grammar: an outline","author":"R Huddleston","year":"1988","unstructured":"Huddleston R (1988) English grammar: an outline. Cambridge University Press, Cambridge"},{"key":"9498_CR62","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1002\/(SICI)1097-4571(199601)47:1<70::AID-ASI7>3.0.CO;2-#","volume":"47","author":"DA Hull","year":"1996","unstructured":"Hull DA (1996) Stemming algorithms\u2014a case study for detailed evaluation. J Am Soc Inf Sci 47:70\u201384","journal-title":"J Am Soc Inf Sci"},{"key":"9498_CR63","unstructured":"Islam M, Uddin M, Khan M (2007) A Light weight stemmer for Bengali and its use in spelling checker. In: Proceedings of the 1st international conference on digital communications and computers"},{"key":"9498_CR64","first-page":"1930","volume":"2","author":"AG Jivani","year":"2011","unstructured":"Jivani AG (2011) A comparative study of stemming algorithms. Int J Comput Technol Appl 2:1930\u20131938","journal-title":"Int J Comput Technol Appl"},{"key":"9498_CR65","doi-asserted-by":"crossref","unstructured":"Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: Proceedings of 10th European conference on machine learning, chapter. Springer, pp 137\u2013142","DOI":"10.1007\/BFb0026683"},{"key":"9498_CR66","doi-asserted-by":"crossref","unstructured":"Jordan C, Healy J, Keselj V (2006) Swordfish: an unsupervised ngram based approach to morphological analysis. In: Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval, pp 657\u2013658","DOI":"10.1145\/1148170.1148303"},{"key":"9498_CR67","doi-asserted-by":"crossref","first-page":"6","DOI":"10.32614\/RJ-2013-001","volume":"5","author":"TP Jurka","year":"2013","unstructured":"Jurka TP, Collingwood L, Boydstun AE et al (2013) RTextTools: a supervised learning package for text classification. R J 5:6\u201312","journal-title":"R J"},{"key":"9498_CR68","first-page":"313","volume":"29","author":"T Kalamboukis","year":"1995","unstructured":"Kalamboukis T, Nikolaidis S (1995) Suffix stripping with modern Greek. Progr Electron Libr Inf Syst 29:313\u2013321","journal-title":"Progr Electron Libr Inf Syst"},{"key":"9498_CR69","unstructured":"Kalamboukis T, Nikolaidis S (1999) An evaluation of stemming algorithms with modern Greek. In: Proceedings of the 7th Hellenic conference on informatics, pp 61\u201370"},{"key":"9498_CR70","doi-asserted-by":"crossref","unstructured":"Kchaou Z, Kanoun S (2008) Arabic stemming with two dictionaries. In: IEEE international conferenece on innovations in information technology, pp 688\u2013691","DOI":"10.1109\/INNOVATIONS.2008.4781780"},{"key":"9498_CR71","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":"9498_CR72","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1145\/324133.324140","volume":"46","author":"J Kleinberg","year":"1999","unstructured":"Kleinberg J (1999) Authoritative sources in a hyperlinked environment. J ACM 46:604\u2013632","journal-title":"J ACM"},{"key":"9498_CR73","doi-asserted-by":"crossref","unstructured":"Konkol M, Konop\u00edk M (2014) Named entity recognition for highly inflectional languages: effects of various lemmatization and stemming approaches. In: Text, speech and dialogue, pp 267\u2013274","DOI":"10.1007\/978-3-319-10816-2_33"},{"key":"9498_CR74","doi-asserted-by":"crossref","unstructured":"Korenius T, Laurikkala J, Jarvelin K, Juhola M (2004) Stemming and lemmatization in the clustering of finnish text documents. In: Proceedings of the thirteenth ACM international conference on information and knowledge management (CIKM\u201904), pp 625\u2013633","DOI":"10.1145\/1031171.1031285"},{"key":"9498_CR75","first-page":"25","volume":"1","author":"W Kraaij","year":"1994","unstructured":"Kraaij W, Pohlman R (1994) Porter\u2019s stemming algorithm for Dutch. New Rev Doc Text Manag 1:25\u201343","journal-title":"New Rev Doc Text Manag"},{"key":"9498_CR76","doi-asserted-by":"crossref","unstructured":"Kraaij W, Pohlman R (1996) Viewing stemming as recall enhancement. In: Proceedings of the 19th annual international ACM SIGIR conference on research and development in information retrieval, pp 40\u201348","DOI":"10.1145\/243199.243209"},{"key":"9498_CR77","doi-asserted-by":"crossref","unstructured":"Krovetz R (1993) Viewing morphology as an inference process. In: Proceedings of the 16th annual international ACM SIGIR conference on research and development in information retrieval, pp 191\u2013202","DOI":"10.1145\/160688.160718"},{"key":"9498_CR78","first-page":"18","volume":"11","author":"D Kumar","year":"2010","unstructured":"Kumar D, Rana P (2010) Design and development of a stemmer for Punjabi. Int J Comput Appl 11:18\u201323","journal-title":"Int J Comput Appl"},{"key":"9498_CR79","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/978-1-4020-6046-5_12","volume":"38","author":"L Larkey","year":"2007","unstructured":"Larkey L, Ballesteros L, Connell ME (2007) Light stemming for Arabic information retrieval. Arab Comput Morphol Text Speech Lang Technol 38:221\u2013243","journal-title":"Arab Comput Morphol Text Speech Lang Technol"},{"key":"9498_CR80","doi-asserted-by":"crossref","unstructured":"Larkey L, 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 conference on research and development in information retrieval (SIGIR \u201902), pp 275\u2013282","DOI":"10.1145\/564376.564425"},{"key":"9498_CR81","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1145\/974740.974746","volume":"2","author":"L Larkey","year":"2003","unstructured":"Larkey L, Connell M, Abdulijaleel N (2003) Hindi CLIR in thirty days. ACM Trans Asian Lang Inf Process 2:130\u2013142","journal-title":"ACM Trans Asian Lang Inf Process"},{"key":"9498_CR82","doi-asserted-by":"crossref","unstructured":"Lavie A, Sagae K, Jayaraman S (2004) The significance of recall in automatic metrics for MT evaluation. In: Machine translation: from real users to research. Springer, pp 134\u2013143","DOI":"10.1007\/978-3-540-30194-3_16"},{"key":"9498_CR83","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1177\/016555158100300403","volume":"3","author":"M Lennon","year":"1981","unstructured":"Lennon M, Peirce DS, Tarry BD, Willett P (1981) An evaluation of some conflation algorithms for information retrieval. J Inf Sci 3:177\u2013183","journal-title":"J Inf Sci"},{"key":"9498_CR84","unstructured":"Lennon M, Pierce DS, Tarry BD, Willett P (1988) An evaluation of some conflation algorithms for information retrieval. In: Document retrieval systems, pp 99\u2013105"},{"key":"9498_CR85","doi-asserted-by":"crossref","unstructured":"Louis A, Nenkova A (2009) Automatically evaluating content selection in summarization without human models. In: Proceedings of the conference on empirical methods in natural language processing, pp 306\u2013314","DOI":"10.3115\/1699510.1699550"},{"key":"9498_CR86","first-page":"22","volume":"11","author":"JB Lovins","year":"1968","unstructured":"Lovins JB (1968) Development of a stemming algorithm. Mech Transl Comput Linguist 11:22\u201331","journal-title":"Mech Transl Comput Linguist"},{"key":"9498_CR87","doi-asserted-by":"crossref","unstructured":"Lushanthan S, Weerasingha A, Hearth D (2014) Morphological analyzer and generator for Tamil language. In: International conference on advances in ICT for emerging regions (ICTer), pp 190\u2013196","DOI":"10.1109\/ICTER.2014.7083900"},{"key":"9498_CR88","unstructured":"Mass D (1996) MPROE\u2014Ein system zur analyse und synthese deutscher W\u00f6rter. In: Hauser R (Ed) Linguistische Verifikation. Max Niemeyer Verlag, T\u00fcbingen"},{"key":"9498_CR89","doi-asserted-by":"crossref","unstructured":"Mahmud M, Afrin M, Razzaque M et al (2014) A rule based Bengali stemmer. In: International conference on advances in computing, communication and informatics, pp 2750\u20132756","DOI":"10.1109\/ICACCI.2014.6968484"},{"key":"9498_CR90","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/978-3-540-74999-8_14","volume":"4730","author":"P Majumder","year":"2007","unstructured":"Majumder P, Mitra M, Datta K (2007a) Statistical vs. rule-based stemming for monolingual french retrieval. Eval Multiling Multi Modal Inf Retr 4730:107\u2013110","journal-title":"Eval Multiling Multi Modal Inf Retr"},{"key":"9498_CR91","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1145\/1281485.1281489","volume":"25","author":"P Majumder","year":"2007","unstructured":"Majumder P, Mitra M, Parui SK et al (2007b) YASS: yet another suffix stripper. ACM Trans Inf Syst 25:18","journal-title":"ACM Trans Inf Syst"},{"key":"9498_CR92","doi-asserted-by":"crossref","unstructured":"Majumder P, Mitra M, Pal D (2008) Bulgarian, Hungarian and Czech stemming using YASS. In: Advances in multilingual and multimodal information retrieval, pp 49\u201356","DOI":"10.1007\/978-3-540-85760-0_6"},{"key":"9498_CR93","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Schutze H (2008) Introduction to information retrieval. Cambridge University Press, New York"},{"key":"9498_CR94","doi-asserted-by":"crossref","unstructured":"Mayfield J, Mcnamee P (2003) Single N-gram stemming. In: Proceedings of the 26th annual international ACM SIGIR conference on research and development of information retrieval, pp 415\u2013416","DOI":"10.1145\/860435.860528"},{"key":"9498_CR95","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P Mcnamee","year":"2004","unstructured":"Mcnamee P, Mayfield J (2004) Character n-gram tokenization for European language text retrieval. Inf Retr Boston 7:73\u201397","journal-title":"Inf Retr Boston"},{"key":"9498_CR96","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 (CIKM\u201903), pp 131\u2013138","DOI":"10.1145\/956863.956889"},{"key":"9498_CR97","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez-Cruz C-F, Torres-Moreno J-M, Medina-Urrea A, Sierra G (2013) Extrinsic evaluation on automatic summarization tasks: testing affixality measurements for statistical word stemming. In: Advances in computational intelligence. Springer, pp 46\u201357","DOI":"10.1007\/978-3-642-37798-3_5"},{"key":"9498_CR98","first-page":"5","volume":"1","author":"D Meyer","year":"2012","unstructured":"Meyer D, Dimitriadou E, Hornik K et al (2012) Misc functions of the department of statistics (e1071), TU Wien. R Packag 1:5\u201324","journal-title":"R Packag"},{"key":"9498_CR99","volume-title":"From document retrieval to question answering","author":"C Monz","year":"2003","unstructured":"Monz C (2003) From document retrieval to question answering. Institute for Logic, Language and Computation, Amsterdam"},{"key":"9498_CR100","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1007\/3-540-45691-0_24","volume":"2046","author":"C Monz","year":"2002","unstructured":"Monz C, Rijke M (2002) Shallow morphological analysis in monolingual information retrieval for Dutch, German, and Italian. Eval Cross Lang Inf Retr Syst 2046:262\u2013277","journal-title":"Eval Cross Lang Inf Retr Syst"},{"key":"9498_CR101","first-page":"1","volume":"19","author":"C Moral","year":"2014","unstructured":"Moral C, Antonio A, Imbert R, Ramirez J (2014) A survey of stemming algorithms in information retrieval. Inf Res 19:1\u201314","journal-title":"Inf Res"},{"key":"9498_CR102","doi-asserted-by":"crossref","unstructured":"Nakov P (2003) Design and evaluation of inflectional stemmer for Bulgarian. In: Proceedings of workshop on Balkan language resources and tools","DOI":"10.1145\/973620.973690"},{"key":"9498_CR103","unstructured":"Ntais G (2006) Development of a stemmer for the Greek language. Master Thesis, Department of Computer and Systems Sciences, Stockholm University"},{"key":"9498_CR104","doi-asserted-by":"crossref","unstructured":"Oard D, Levow G, Cabezas C (2001) CLEF experiments at Maryland? Statistical stemming and backoff translation. In: Proceedings of the workshop of cross-language evaluation forum on cross language information retrieval and evaluation. Springer, Berlin, pp 176\u2013187","DOI":"10.1007\/3-540-44645-1_17"},{"key":"9498_CR105","unstructured":"Open American National Corpus. http:\/\/www.anc.org\/data\/oanc"},{"key":"9498_CR106","doi-asserted-by":"crossref","unstructured":"Orengo V, Huyck C (2001) A stemming algorithm for the Portuguese language. In: Proceedings of 8th internatioanl symposium on string processing and information retrieval, pp 186\u2013193","DOI":"10.1109\/SPIRE.2001.989755"},{"key":"9498_CR107","unstructured":"Othman R (1993) Footer Malay word for document retrieval system. M.Sc. Thesis. National University of Malaysia"},{"key":"9498_CR108","doi-asserted-by":"crossref","unstructured":"Ounis I, Amati G, Plachouras V, et al (2006) Terrier: a high performance and scalable information retrieval platform. In: Proceedings of ACM SIGIR\u201906 workshop on open source information retrieval (OSIR 2006)","DOI":"10.1007\/978-3-540-31865-1_37"},{"key":"9498_CR109","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/101306.101310","volume":"24","author":"CD Paice","year":"1990","unstructured":"Paice CD (1990) Another stemmer. ACM SIGIR Forum 24:56\u201361","journal-title":"ACM SIGIR Forum"},{"key":"9498_CR110","doi-asserted-by":"crossref","unstructured":"Paice CD (1994) An evaluation method for stemming algorithms. In: Proceedings of the 17th annual international ACM SIGIR conference on research and development in information retrieval, pp 42\u201350","DOI":"10.1007\/978-1-4471-2099-5_5"},{"key":"9498_CR111","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2037661.2037664","volume":"29","author":"J Paik","year":"2011","unstructured":"Paik J, Mitra M, Parui S, Jarvelin K (2011a) GRAS: an effective and efficient stemming algorithm for information retrieval. ACM Trans Inf Syst 29:1\u201324","journal-title":"ACM Trans Inf Syst"},{"key":"9498_CR112","doi-asserted-by":"crossref","unstructured":"Paik JH, Pal D, Parui SK (2011c) A novel corpus-based stemming algorithm using co-occurrence statistics. In: Proceedings of the 34th annual international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201911). ACM, New York, pp 863\u2013872","DOI":"10.1145\/2009916.2010031"},{"key":"9498_CR113","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1967293.1967295","volume":"10","author":"JH Paik","year":"2011","unstructured":"Paik JH, Parui SK (2011b) A fast corpus-based stemmer. ACM Trans Asian Lang Inf Process 10:1\u201316. doi: 10.1145\/1967293.1967295","journal-title":"ACM Trans Asian Lang Inf Process"},{"key":"9498_CR114","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2536736.2536738","volume":"31","author":"JH Paik","year":"2013","unstructured":"Paik JH, Parui SK, Pal D, Robertson SE (2013) Effective and robust query-based stemming. ACM Trans Inf Syst 31:1\u201329. doi: 10.1145\/2536736.2536738","journal-title":"ACM Trans Inf Syst"},{"key":"9498_CR115","unstructured":"Patel P, Popat K, Bhattacharyya P (2010) Hybrid stemmer for Gujarati. In: Proceedings of the 23rd international conference on computational linguistics (COLING), pp 51\u201355"},{"key":"9498_CR116","doi-asserted-by":"crossref","unstructured":"Peng F, Ahmed N, Li X, Lu Y (2007) Context sensitive stemming for web search. In: Proceedings of the 30th annual International ACM SIGIR conference on research and development in information retrieval\u2014SIGIR \u201907. ACM Press, New York, p 639","DOI":"10.1145\/1277741.1277851"},{"key":"9498_CR117","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1002\/(SICI)1097-4571(199206)43:5<384::AID-ASI6>3.0.CO;2-L","volume":"43","author":"M Popovic","year":"1992","unstructured":"Popovic M, Willet P (1992) The effectiveness of stemming for natural-language access to Slovene textual data. J Am Soc Inf Sci 43:384\u2013390","journal-title":"J Am Soc Inf Sci"},{"key":"9498_CR118","first-page":"130","volume":"14","author":"MF Porter","year":"1980","unstructured":"Porter MF (1980) An algorithm for suffix stripping. Progr Electron Libr Inf Syst 14:130\u2013137","journal-title":"Progr Electron Libr Inf Syst"},{"key":"9498_CR119","unstructured":"Porter MF (2001) Snowball: a language for stemming algorithms. http:\/\/snowball.tartarus.org"},{"key":"9498_CR120","doi-asserted-by":"crossref","unstructured":"Ramachandran V, Krishnamurthi I (2012) An iterative stemmer for Tamil language. In: Proceedings of the 4th Asian conference, ACIIDS 2012, pp 197\u2013205","DOI":"10.1007\/978-3-642-28493-9_22"},{"key":"9498_CR121","unstructured":"Ramanathan A, Hegde J, Shah RM, et al (2008) Simple syntactic and morphological processing can help English\u2013Hindi statistical machine translation. In: International joint conference on natural language processing, pp 513\u2013520"},{"key":"9498_CR122","unstructured":"Ramanathan A, Rao D (2003) A lightweight stemmer for Hindi. In: Proceedings of the 10th conference of the European chapter of the association for computational linguistics"},{"key":"9498_CR123","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/S0306-4573(99)00046-1","volume":"36","author":"SE Robertson","year":"2000","unstructured":"Robertson SE, Walker S, Beaulieu M (2000) Experimentation as a way of life: Okapi at TREC. Inf Process Manag 36:95\u2013108","journal-title":"Inf Process Manag"},{"key":"9498_CR124","unstructured":"Rosell M (2003) Improving clustering of Swedish newspaper articles using stemming and compound splitting. In: NoDaLiDa 2003, Reykjavik, Iceland 2003, pp 1\u20137"},{"key":"9498_CR125","volume-title":"The SMART retrieval system\u2014experiments in automatic document retrieval","author":"G Salton","year":"1971","unstructured":"Salton G, McGill M (1971) The SMART retrieval system\u2014experiments in automatic document retrieval. Prentice Hall Inc., Englewood Cliffs"},{"key":"9498_CR126","first-page":"352","volume":"8","author":"N Sandhya","year":"2011","unstructured":"Sandhya N, Lalitha YS, Sowmya V et al (2011) Analysis of stemming algorithm for text clustering. IJCSI Int J Comput Sci Issues 8:352\u2013359","journal-title":"IJCSI Int J Comput Sci Issues"},{"key":"9498_CR127","doi-asserted-by":"crossref","first-page":"944","DOI":"10.1002\/(SICI)1097-4571(1999)50:10<944::AID-ASI9>3.0.CO;2-Q","volume":"50","author":"J Savoy","year":"1999","unstructured":"Savoy J (1999) A stemming procedure and stopword list for general French corpora. J Am Soc Inf Sci 50:944\u2013952","journal-title":"J Am Soc Inf Sci"},{"key":"9498_CR128","doi-asserted-by":"crossref","unstructured":"Savoy J (2006) Light stemming approaches for the French, Portuguese, German and Hungarian languages. In: Proceedings of the 2006 ACM symposium on applied computing, pp 1031\u20131035","DOI":"10.1145\/1141277.1141523"},{"key":"9498_CR129","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.ipm.2007.01.022","volume":"44","author":"J Savoy","year":"2008","unstructured":"Savoy J (2008) Searching strategies for the Hungarian language. Inf Process Manag 44:310\u2013324","journal-title":"Inf Process Manag"},{"key":"9498_CR130","doi-asserted-by":"crossref","unstructured":"Savoy J, Berger P-Y (2006) Monolingual, Bilingual, and GIRT information retrieval at CLEF-2005. In: 6th workshop of the cross-language evalution forum, CLEF 2005, pp 131\u2013140","DOI":"10.1007\/11878773_14"},{"key":"9498_CR131","unstructured":"Sembok T (2005) Word stemming algorithms and retrieval effectiveness in Malay and Arabic documents retrieval systems. In: Proceedings of the world academy of science, engineering and technology"},{"key":"9498_CR132","doi-asserted-by":"crossref","unstructured":"Sever H, Bitirim Y (2003) FindStem: analysis and evaluation of a Turkish stemming algorithm. In: Proceedings of the 10th international symposium on string processing and information retrieval, pp 238\u2013251","DOI":"10.1007\/978-3-540-39984-1_18"},{"key":"9498_CR133","unstructured":"Sharifloo A, Shamsfard M (2008) A bottom up approach to persian stemming. In: Proceedings of the third international joint conference on natural language processing"},{"key":"9498_CR134","unstructured":"Shrivastava M, Bhattacharyya P (2008) Hindi POS tagger using naive stemming: harnessing morphological information without extensive linguistic knowledge. In: Proceedings of international conference on NLP (ICON08)"},{"key":"9498_CR135","unstructured":"Shrivastava M, Mohapatra B, Bhattacharyya P et al (2005) Morphology based natural language processing tools for Indian languages. In: Proceedings of the 4th annual international research student seminar in computer science"},{"key":"9498_CR136","unstructured":"Smirnov I (2008) Overview of stemming algorithms. In: Mechanical Translation. http:\/\/thesmirnovs.org\/info\/stemming.pdf . Accessed 25 May 2014"},{"key":"9498_CR137","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1109\/TLA.2009.5349047","volume":"7","author":"MVB Soares","year":"2009","unstructured":"Soares MVB, Prati RC, Monard MC (2009) Improvement on the Porter\u2019s stemming algorithm for Portuguese. IEEE Lat Am Trans 7:472\u2013477","journal-title":"IEEE Lat Am Trans"},{"key":"9498_CR138","doi-asserted-by":"crossref","unstructured":"Stein B, Potthast M (2007) Putting successor variety stemming to work. In: Advances in data analysis. Springer, pp 367\u2013374","DOI":"10.1007\/978-3-540-70981-7_41"},{"key":"9498_CR139","unstructured":"Suba K, Jiandani D, Bhattacharyya P (2011) Hybrid inflectional stemmer and rule-based derivational stemmer for Gujarati. In: Sangal R, Malik M (eds) Proceedings of the 23rd workshop on south and southeast Asian natural language processing (WSSANLP). Asian Federation of Natural Language Processing, Chiang Mai, Thailand, pp 1\u20138"},{"key":"9498_CR140","doi-asserted-by":"crossref","unstructured":"Taghva K, Elkhoury R, Coombs J (2005) Arabic stemming without a root dictionary. In: Proceedings of the International conference on information technology: coding and computing (ITCC\u201905), pp 152\u2013157","DOI":"10.1109\/ITCC.2005.90"},{"key":"9498_CR141","doi-asserted-by":"crossref","unstructured":"Tai S, Ong C, Abdullah N (2000) On designing an automated Malaysian stemmer for the Malay language. In: Proceedings of the fifth international workshop on information retrieval with Asian languages, pp 207\u2013208","DOI":"10.1145\/355214.355247"},{"key":"9498_CR142","unstructured":"Tala F (2003) A study of stemming effects on information retrieval in Bahasa Indonesia. Master Thesis, University of Amsterdam"},{"key":"9498_CR143","unstructured":"Terrier information retrieval platform. http:\/\/terrier.org"},{"key":"9498_CR144","unstructured":"The lemur project. http:\/\/www.lemurproject.org"},{"key":"9498_CR145","unstructured":"The R project for statistical computing. http:\/\/www.r-project.org"},{"key":"9498_CR146","unstructured":"Toutanova K, Suzuki H, Ruopp A (2008) Applying morphology generation models to machine translation. In: Association for computational linguistics, pp 514\u2013522"},{"key":"9498_CR147","unstructured":"Xapian project website. http:\/\/xapian.org"},{"key":"9498_CR148","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1145\/267954.267957","volume":"16","author":"J Xu","year":"1998","unstructured":"Xu J, Croft WB (1998) Corpus-based stemming using cooccurrence of word variants. ACM Trans Inf Syst 16:61\u201381","journal-title":"ACM Trans Inf Syst"},{"key":"9498_CR149","unstructured":"Yadav A, Yadav R, Pal S (2012) ISM@FIRE-2012 adhoc retrieval and morpheme extraction task. In: Post proceedings of FIRE-2012"},{"key":"9498_CR150","doi-asserted-by":"crossref","unstructured":"Zollmann A, Venugopal A, Vogel S (2006) Bridging the inflection morphology gap for Arabic statistical machine translation. In: Proceedings of the human language technology, pp 201\u2013204","DOI":"10.3115\/1614049.1614100"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-016-9498-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9498-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9498-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-016-9498-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T17:22:49Z","timestamp":1656955369000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-016-9498-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,1]]},"references-count":150,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["9498"],"URL":"https:\/\/doi.org\/10.1007\/s10462-016-9498-2","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,8,1]]}}}