{"id":"https://openalex.org/W1998824124","doi":"https://doi.org/10.1145/1390334.1390518","title":"Don't have a stemmer?","display_name":"Don't have a stemmer?","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W1998824124","doi":"https://doi.org/10.1145/1390334.1390518","mag":"1998824124"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual 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":["University of Maryland Baltimore County, Baltimore, MD, USA","University of Maryland Baltimore County, baltimore, MD, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]},{"raw_affiliation_string":"University of Maryland Baltimore County, baltimore, MD, USA#TAB#","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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7761151194572449},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7396999597549438},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7022358179092407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6713637113571167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6190392971038818},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6065350770950317},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5077568292617798},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.4381343126296997},{"id":"https://openalex.org/keywords/automatic-indexing","display_name":"Automatic indexing","score":0.4317844808101654},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34867027401924133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16840919852256775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761151194572449},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7396999597549438},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7022358179092407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6713637113571167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6190392971038818},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6065350770950317},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5077568292617798},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.4381343126296997},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.4317844808101654},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34867027401924133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16840919852256775},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390334.1390518","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1971285215","https://openalex.org/W1979076595","https://openalex.org/W2029097226","https://openalex.org/W2058200372","https://openalex.org/W2098162425","https://openalex.org/W2117621558","https://openalex.org/W2120220342","https://openalex.org/W2120365765","https://openalex.org/W2915906546","https://openalex.org/W6678082820"],"related_works":["https://openalex.org/W204619012","https://openalex.org/W2398073981","https://openalex.org/W2051392313","https://openalex.org/W4247874641","https://openalex.org/W2081057833","https://openalex.org/W2139991891","https://openalex.org/W2025451713","https://openalex.org/W2062327384","https://openalex.org/W2168066506","https://openalex.org/W2008087111"],"abstract_inverted_index":{"The":[0],"choice":[1],"of":[2,33,65,118],"indexing":[3],"terms":[4,43],"used":[5],"to":[6,24,29,41,72,115],"represent":[7],"documents":[8,36],"crucially":[9],"determines":[10],"how":[11],"e":[12],"ective":[13],"subsequent":[14],"retrieval":[15],"will":[16],"be.":[17],"IR":[18],"systems":[19],"commonly":[20],"use":[21,117],"rule-based":[22,100],"stemmers":[23,51],"normalize":[25],"surface":[26],"word":[27],"forms":[28],"combat":[30],"the":[31,63,116,127],"problem":[32],"not":[34,53],"finding":[35,121],"that":[37,83,122],"contain":[38],"words":[39],"related":[40],"query":[42],"by":[44,95],"inflectional":[45],"or":[46],"derivational":[47],"morphology.":[48],"But":[49],"such":[50],"are":[52],"available":[54],"in":[55,77,92,106],"all":[56],"languages.":[57,80,109],"In":[58],"this":[59],"paper":[60],"we":[61],"explore":[62],"effectiveness":[64],"unsupervised":[66,84],"morphological":[67],"segmentation":[68,85],"as":[69],"an":[70],"alternative":[71],"stemming":[73],"using":[74],"test":[75],"sets":[76],"thirteen":[78],"European":[79],"We":[81,110],"find":[82],"is":[86,104],"significantly":[87],"better":[88,105],"than":[89,97],"unnormalized":[90],"words,":[91],"several":[93],"cases":[94],"more":[96],"20%.":[98],"However,":[99],"stemming,":[101],"if":[102],"available,":[103],"low":[107],"complexity":[108],"also":[111],"compare":[112],"these":[113],"methods":[114],"character":[119],"n-grams,":[120],"on":[123],"average":[124],"n-grams":[125],"yield":[126],"best":[128],"performance.":[129]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}