{"id":"https://openalex.org/W2148645628","doi":"https://doi.org/10.1145/1460027.1460035","title":"Indexing and retrieval of a Greek corpus","display_name":"Indexing and retrieval of a Greek corpus","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2148645628","doi":"https://doi.org/10.1145/1460027.1460035","mag":"2148645628"},"language":"en","primary_location":{"id":"doi:10.1145/1460027.1460035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460027.1460035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Improving non english web searching","raw_type":"proceedings-article"},"type":"paratext","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/A5076122659","display_name":"George Paltoglou","orcid":"https://orcid.org/0000-0003-4300-7061"},"institutions":[{"id":"https://openalex.org/I192756129","display_name":"University of Macedonia","ror":"https://ror.org/05fg6gr82","country_code":"GR","type":"education","lineage":["https://openalex.org/I192756129"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Paltoglou","raw_affiliation_strings":["University of Macedonia, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macedonia, Thessaloniki, Greece","institution_ids":["https://openalex.org/I192756129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047037650","display_name":"Michail Salampasis","orcid":"https://orcid.org/0000-0003-4087-125X"},"institutions":[{"id":"https://openalex.org/I77990126","display_name":"Alexander Technological Educational Institute of Thessaloniki","ror":"https://ror.org/04h36ea57","country_code":"GR","type":"education","lineage":["https://openalex.org/I77990126"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Michail Salampasis","raw_affiliation_strings":["Alexander Technological Educational Institute of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexander Technological Educational Institute of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I77990126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091565834","display_name":"Fotis Lazarinis","orcid":"https://orcid.org/0000-0002-4653-7212"},"institutions":[{"id":"https://openalex.org/I1319660883","display_name":"Technological Educational Institute of Western Greece","ror":"https://ror.org/01mymm084","country_code":"GR","type":"education","lineage":["https://openalex.org/I1319660883"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Fotis Lazarinis","raw_affiliation_strings":["Technological Educational Institute of Mesolonghi, Mesolonghi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Educational Institute of Mesolonghi, Mesolonghi, Greece","institution_ids":["https://openalex.org/I1319660883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"54"},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.9958999752998352,"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":0.7887839078903198},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6008296012878418},{"id":"https://openalex.org/keywords/lingua-franca","display_name":"Lingua franca","score":0.5976351499557495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5763934254646301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176032781600952},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5017800331115723},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.481332391500473},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4707161784172058},{"id":"https://openalex.org/keywords/greek-language","display_name":"Greek language","score":0.42834293842315674},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4241713583469391},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4112715721130371},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3105722665786743},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27662548422813416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09236946702003479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887839078903198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6008296012878418},{"id":"https://openalex.org/C159789966","wikidata":"https://www.wikidata.org/wiki/Q80839","display_name":"Lingua franca","level":2,"score":0.5976351499557495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5763934254646301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176032781600952},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5017800331115723},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.481332391500473},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4707161784172058},{"id":"https://openalex.org/C2994462464","wikidata":"https://www.wikidata.org/wiki/Q9129","display_name":"Greek language","level":2,"score":0.42834293842315674},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4241713583469391},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4112715721130371},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3105722665786743},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27662548422813416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09236946702003479},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1460027.1460035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460027.1460035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Improving non english web searching","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W172597201","https://openalex.org/W1494864219","https://openalex.org/W1973952533","https://openalex.org/W1985180788","https://openalex.org/W1999257126","https://openalex.org/W2006467333","https://openalex.org/W2026926922","https://openalex.org/W2086377957","https://openalex.org/W2097284241","https://openalex.org/W2098162425","https://openalex.org/W2145143501","https://openalex.org/W2154724067","https://openalex.org/W2187636165","https://openalex.org/W6629627396","https://openalex.org/W6646522093","https://openalex.org/W6674809828"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W3193328749","https://openalex.org/W4242844568"],"abstract_inverted_index":{"Greek":[0,53,82,168],"is":[1,25,67],"one":[2],"of":[3,36,47,59,79,104,107,142,154],"the":[4,21,33,52,63,77,102,105,111,132,165],"most":[5],"difficult":[6],"languages":[7],"to":[8,61,100,128,163],"handle":[9,148],"in":[10,73,85,98,110,126,167],"Web":[11,90],"Information":[12],"Retrieval":[13],"(IR)":[14],"related":[15],"tasks.":[16,170],"Its":[17],"difficulty":[18],"stems":[19],"from":[20,51],"fact":[22],"that":[23,49,66,135],"it":[24],"grammatically,":[26],"morphologically":[27],"and":[28,88,116,122,138,144,146],"orthographically":[29],"more":[30],"complex":[31],"than":[32],"lingua":[34],"franca":[35],"IR,":[37],"English.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"address":[43],"a":[44,57,81,86,94,151],"significant":[45],"number":[46,58],"issues":[48],"originate":[50],"language.":[54],"We":[55,75,92,118],"use":[56],"techniques":[60],"determine":[62],"correct":[64],"encoding":[65],"used":[68,109],"by":[69],"web":[70],"pages":[71],"written":[72],"Greek.":[74,155],"test":[76],"effect":[78],"using":[80],"stopword":[83],"list":[84],"realistic":[87],"controlled":[89],"environment.":[91],"employ":[93],"character":[95],"mapping":[96],"scheme,":[97],"order":[99,127],"overcome":[101],"problem":[103],"diversity":[106],"diacritics":[108],"language,":[112],"such":[113],"as":[114],"accents":[115],"diaeresis.":[117],"utilize":[119],"word":[120],"distance":[121],"fuzzy":[123],"similarity":[124],"metrics":[125],"make":[129],"up":[130],"for":[131],"different":[133],"forms":[134],"nouns,":[136],"verbs":[137],"articles":[139],"appear":[140],"because":[141],"conjugations":[143],"inflections":[145],"additionally":[147],"greeklish":[149],"queries,":[150],"transliterated":[152],"form":[153],"The":[156],"conducted":[157],"experiments":[158],"present":[159],"some":[160],"effective":[161],"ways":[162],"increase":[164],"accuracy":[166],"IR":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
