{"id":"https://openalex.org/W2054364203","doi":"https://doi.org/10.1145/1571941.1571957","title":"Addressing morphological variation in alphabetic languages","display_name":"Addressing morphological variation in alphabetic languages","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2054364203","doi":"https://doi.org/10.1145/1571941.1571957","mag":"2054364203"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1571957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046292035","display_name":"Paul McNamee","orcid":"https://orcid.org/0000-0002-4540-8718"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul McNamee","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025012064","display_name":"Charles Nicholas","orcid":"https://orcid.org/0000-0001-9494-7139"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["UMBC, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMBC, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036270568","display_name":"James Mayfield","orcid":"https://orcid.org/0000-0003-3866-3013"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8467979431152344},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6137286424636841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5751940011978149},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.5728455185890198},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5359903573989868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5311471223831177},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4968109428882599},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4813466966152191},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4030156135559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467979431152344},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6137286424636841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5751940011978149},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.5728455185890198},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5359903573989868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311471223831177},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4968109428882599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4813466966152191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4030156135559082},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1571941.1571957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W100509257","https://openalex.org/W1530230826","https://openalex.org/W1971285215","https://openalex.org/W1979076595","https://openalex.org/W1979135380","https://openalex.org/W1993128997","https://openalex.org/W1998328714","https://openalex.org/W2008495066","https://openalex.org/W2020647130","https://openalex.org/W2029097226","https://openalex.org/W2038114184","https://openalex.org/W2039660096","https://openalex.org/W2058200372","https://openalex.org/W2068143774","https://openalex.org/W2089656898","https://openalex.org/W2093537029","https://openalex.org/W2095368471","https://openalex.org/W2100259670","https://openalex.org/W2102712128","https://openalex.org/W2117621558","https://openalex.org/W2120220342","https://openalex.org/W2131133093","https://openalex.org/W2146798791","https://openalex.org/W2305803660","https://openalex.org/W2326587081","https://openalex.org/W2442629089","https://openalex.org/W2593270255","https://openalex.org/W3198160809","https://openalex.org/W6678082820"],"related_works":["https://openalex.org/W2887281027","https://openalex.org/W4288429387","https://openalex.org/W1552656226","https://openalex.org/W2807873899","https://openalex.org/W3098552971","https://openalex.org/W282478887","https://openalex.org/W4288376155","https://openalex.org/W2357010009","https://openalex.org/W2927851123","https://openalex.org/W2184000611"],"abstract_inverted_index":{"The":[0],"selection":[1],"of":[2,34,79],"indexing":[3],"terms":[4,44],"for":[5,56,65,81],"representing":[6,82],"documents":[7,37],"is":[8,61],"a":[9],"key":[10],"decision":[11],"that":[12,38],"limits":[13],"how":[14],"effective":[15],"subsequent":[16],"retrieval":[17],"can":[18],"be.":[19],"Often":[20],"stemming":[21],"algorithms":[22],"are":[23,53,69],"used":[24],"to":[25,42],"normalize":[26],"surface":[27],"forms,":[28],"and":[29,59,84,94],"thereby":[30],"address":[31],"the":[32],"problem":[33],"not":[35,54],"finding":[36],"contain":[39],"words":[40],"related":[41],"query":[43],"through":[45],"infectional":[46],"or":[47],"derivational":[48],"morphology.":[49],"However,":[50],"rule-based":[51],"stemmers":[52],"available":[55],"every":[57],"language":[58],"it":[60],"unclear":[62],"which":[63],"methods":[64],"coping":[66],"with":[67],"morphology":[68],"most":[70],"effective.":[71],"In":[72],"this":[73],"paper":[74],"we":[75],"investigate":[76],"an":[77],"assortment":[78],"techniques":[80],"text":[83],"compare":[85],"these":[86],"approaches":[87],"using":[88],"data":[89],"sets":[90],"in":[91],"eighteen":[92],"languages":[93],"five":[95],"different":[96],"writing":[97],"systems.":[98]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}