{"id":"https://openalex.org/W1987944752","doi":"https://doi.org/10.1017/s1351324906004256","title":"Using shallow linguistic analysis to improve search on Danish compounds","display_name":"Using shallow linguistic analysis to improve search on Danish compounds","publication_year":2006,"publication_date":"2006-06-09","ids":{"openalex":"https://openalex.org/W1987944752","doi":"https://doi.org/10.1017/s1351324906004256","mag":"1987944752"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324906004256","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004256","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","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/A5112741673","display_name":"Bolette Sandford Pedersen","orcid":null},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"BOLETTE SANDFORD PEDERSEN","raw_affiliation_strings":["Center for Sprogteknologi, University of Copenhagen, Njalsgade 80, DK-2300 S, Denmark e-mail:","Center for Sprogteknologi, University of Copenhagen, Njalsgade 80, DK-2300 S, Denmark e-mail: [email\u00a0protected]#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Sprogteknologi, University of Copenhagen, Njalsgade 80, DK-2300 S, Denmark e-mail:","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Center for Sprogteknologi, University of Copenhagen, Njalsgade 80, DK-2300 S, Denmark e-mail: [email\u00a0protected]#TAB#","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112741673"],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":2.7962,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90538854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"1","first_page":"75","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7632619142532349},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6345729827880859},{"id":"https://openalex.org/keywords/danish","display_name":"Danish","score":0.6229845285415649},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5775400400161743},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.5498566031455994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4770236015319824},{"id":"https://openalex.org/keywords/phrase-search","display_name":"Phrase search","score":0.45550087094306946},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.449938029050827},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4422287940979004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.392581045627594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3747522830963135},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3100738525390625},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.3064761757850647},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2794095277786255},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.25293704867362976},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1005663275718689},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.09085920453071594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632619142532349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6345729827880859},{"id":"https://openalex.org/C164622146","wikidata":"https://www.wikidata.org/wiki/Q9035","display_name":"Danish","level":2,"score":0.6229845285415649},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5775400400161743},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.5498566031455994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4770236015319824},{"id":"https://openalex.org/C37202355","wikidata":"https://www.wikidata.org/wiki/Q7188071","display_name":"Phrase search","level":5,"score":0.45550087094306946},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.449938029050827},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4422287940979004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.392581045627594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3747522830963135},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3100738525390625},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.3064761757850647},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2794095277786255},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.25293704867362976},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1005663275718689},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.09085920453071594},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324906004256","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004256","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3592ab10-06d8-11dd-bee9-02004c4f4f50","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/3592ab10-06d8-11dd-bee9-02004c4f4f50","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pedersen , B S 2007 , ' Using shallow linguistic analysis to improve search on Danish compounds ' , Natural Language Engineering , vol. 13 , no. 1 , pp. 75-90 .","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"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":18,"referenced_works":["https://openalex.org/W77389282","https://openalex.org/W160841727","https://openalex.org/W1484701727","https://openalex.org/W1560716299","https://openalex.org/W1572948005","https://openalex.org/W1577834605","https://openalex.org/W1926320601","https://openalex.org/W1941999406","https://openalex.org/W1979965310","https://openalex.org/W2027666258","https://openalex.org/W2035967403","https://openalex.org/W2045577803","https://openalex.org/W2076145704","https://openalex.org/W2100860490","https://openalex.org/W2101801316","https://openalex.org/W2105106523","https://openalex.org/W2133702079","https://openalex.org/W2140354722"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W1521725692","https://openalex.org/W2800106761","https://openalex.org/W2919747665","https://openalex.org/W3008917487","https://openalex.org/W2901901036","https://openalex.org/W3197639690","https://openalex.org/W2572349046","https://openalex.org/W2049540727","https://openalex.org/W2185998359"],"abstract_inverted_index":{"In":[0,149],"this":[1,105,111,150,248],"paper":[2,112],"we":[3,118,152,227],"focus":[4],"on":[5,14,124,261,272],"a":[6,27,66,81,198,217,229,235,256],"specific":[7,28],"search-related":[8],"query":[9,60],"expansion":[10,18,57,106],"topic,":[11],"namely":[12],"search":[13,122,175,180,207,225,279],"Danish":[15,48],"compounds":[16,161],"and":[17,49,172,233],"to":[19,91,115,165,196,201],"some":[20,158],"of":[21,58,68,80,96,110,134,160,265,275,286],"their":[22],"synonymous":[23,74,167,199],"phrases.":[24],"Compounds":[25],"constitute":[26],"issue":[29],"in":[30,32,34,40,76,143,188],"search,":[31],"particular":[33],"languages":[35],"where":[36,177],"they":[37],"are":[38,162,193,214],"written":[39],"one":[41],"word,":[42],"as":[43,216,269,271],"is":[44,65,89,99,113],"the":[45,50,59,70,78,94,131,135,141,145,179,185,189,202,262,266,273,284],"case":[46],"for":[47,220,240],"other":[51],"Scandinavian":[52],"languages.":[53],"For":[54],"such":[55],"languages,":[56],"compound":[61,82,147,204,212,252,267],"into":[62],"separate":[63],"lemmas":[64],"way":[67],"finding":[69],"often":[71],"frequent":[72],"alternative":[73],"phrases":[75],"which":[77,144],"content":[79],"can":[83,119,277],"also":[84],"be":[85],"expressed.":[86],"However,":[87],"it":[88],"crucial":[90],"note":[92],"that":[93,157,174,251],"number":[95,285],"irrelevant":[97,287],"hits":[98],"generally":[100],"very":[101],"high":[102],"when":[103],"using":[104,247],"strategy.":[107],"The":[108,206,243],"aim":[109],"therefore":[114],"examine":[116],"how":[117],"obtain":[120],"better":[121],"results":[123,176,208,244],"split":[125,146],"compounds,":[126],"partly":[127,138],"by":[128,139,183,246,280],"looking":[129],"at":[130],"internal":[132],"structure":[133,264],"original":[136,203],"compound,":[137],"analyzing":[140],"context":[142],"occurs.":[148],"context,":[151],"pursue":[153],"two":[154],"hypotheses:":[155],"(1)":[156],"categories":[159],"more":[163,194],"likely":[164,195],"have":[166],"\u2018split\u2019":[168],"counterparts":[169],"than":[170],"others;":[171],"(2)":[173],"both":[178],"words":[181],"(obtained":[182],"splitting":[184,253],"compound)":[186],"occur":[187],"same":[190],"noun":[191],"phrase,":[192],"contain":[197],"phrase":[200],"query.":[205],"from":[209],"410":[210],"enhanced":[211],"queries":[213],"used":[215],"test":[218],"bed":[219],"our":[221],"experiments.":[222],"On":[223],"these":[224],"results,":[226],"perform":[228],"shallow":[230,257],"linguistic":[231,258],"analysis":[232,259],"introduce":[234],"new,":[236],"linguistically":[237],"based":[238],"threshold":[239],"retrieved":[241],"hits.":[242,288],"obtained":[245],"strategy":[249],"demonstrate":[250],"combined":[254],"with":[255],"focusing":[260],"argument":[263],"head":[268],"well":[270],"recognition":[274],"NPs,":[276],"improve":[278],"substantially":[281],"bringing":[282],"down":[283]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
