{"id":"https://openalex.org/W1993868383","doi":"https://doi.org/10.1145/2494188.2494195","title":"Extracting Knowledge from Wikipedia Articles through Distributed Semantic Analysis","display_name":"Extracting Knowledge from Wikipedia Articles through Distributed Semantic Analysis","publication_year":2013,"publication_date":"2013-09-04","ids":{"openalex":"https://openalex.org/W1993868383","doi":"https://doi.org/10.1145/2494188.2494195","mag":"1993868383"},"language":"en","primary_location":{"id":"doi:10.1145/2494188.2494195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494188.2494195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Knowledge Management and Knowledge Technologies","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/A5066308873","display_name":"Nguyen Trung Hieu","orcid":"https://orcid.org/0000-0002-2157-2222"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Nguyen Trung Hieu","raw_affiliation_strings":["Department of Computer Science and Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050457902","display_name":"Mario Di Francesco","orcid":"https://orcid.org/0000-0003-1351-1988"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mario Di Francesco","raw_affiliation_strings":["Department of Computer Science and Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034913796","display_name":"Antti Yl\u00e4-J\u00e4\u00e4ski","orcid":"https://orcid.org/0000-0002-2069-1721"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Antti Yl\u00e4-J\u00e4\u00e4ski","raw_affiliation_strings":["Department of Computer Science and Engineering, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.6864,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6733833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9925000071525574,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9914000034332275,"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":0.8922098875045776},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.7575558423995972},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6063502430915833},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5465819239616394},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5428947806358337},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.479924738407135},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4652802348136902},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.43647122383117676},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.41757458448410034},{"id":"https://openalex.org/keywords/semantic-analysis","display_name":"Semantic analysis (machine learning)","score":0.4135643541812897},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39352476596832275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.386604905128479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38303375244140625},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.2651549279689789},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.14971300959587097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8922098875045776},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.7575558423995972},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6063502430915833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5465819239616394},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5428947806358337},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.479924738407135},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4652802348136902},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.43647122383117676},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.41757458448410034},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.4135643541812897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39352476596832275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.386604905128479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38303375244140625},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2651549279689789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.14971300959587097},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2494188.2494195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494188.2494195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Knowledge Management and Knowledge Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W158057341","https://openalex.org/W176211028","https://openalex.org/W603723648","https://openalex.org/W1606292664","https://openalex.org/W1959533457","https://openalex.org/W1960027552","https://openalex.org/W1966979133","https://openalex.org/W2026487812","https://openalex.org/W2053921957","https://openalex.org/W2070921031","https://openalex.org/W2080100102","https://openalex.org/W2099938389","https://openalex.org/W2103318667","https://openalex.org/W2105313627","https://openalex.org/W2107484888","https://openalex.org/W2120779048","https://openalex.org/W2123457740","https://openalex.org/W2136930489","https://openalex.org/W2158997610","https://openalex.org/W2173213060","https://openalex.org/W2608239929","https://openalex.org/W3001753394","https://openalex.org/W3216404684","https://openalex.org/W6618549861","https://openalex.org/W6636127415"],"related_works":["https://openalex.org/W1965623300","https://openalex.org/W3134365128","https://openalex.org/W2135511601","https://openalex.org/W2541135911","https://openalex.org/W2359259132","https://openalex.org/W4387489691","https://openalex.org/W2103835134","https://openalex.org/W858433989","https://openalex.org/W2250580948","https://openalex.org/W2078911128"],"abstract_inverted_index":{"Computing":[0],"semantic":[1,12,55,85],"word":[2,67],"similarity":[3],"and":[4,106],"relatedness":[5,86,171],"requires":[6],"access":[7],"to":[8,23,127,142],"vast":[9],"amounts":[10],"of":[11,31,61,84,101,121,151,169],"space":[13],"for":[14,158],"effective":[15],"analysis.":[16,56],"As":[17],"a":[18,28,34,42,51,59,165],"consequence,":[19],"it":[20],"is":[21,97,155,182],"time-consuming":[22],"extract":[24],"useful":[25],"information":[26],"from":[27],"large":[29],"amount":[30],"data":[32],"on":[33,77,99],"single":[35],"workstation.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"system,":[43],"called":[44],"Distributed":[45],"Semantic":[46,130],"Analysis":[47,131],"(DSA),":[48],"that":[49,154],"integrates":[50],"distributed-based":[52],"approach":[53,136],"with":[54,65,124,172],"DSA":[57,80,163],"builds":[58],"list":[60],"concept":[62,145],"vectors":[63],"associated":[64],"each":[66],"by":[68,73,176],"exploiting":[69],"the":[70,82,91,102,107,119,122,128,139,144,149,156,188],"knowledge":[71],"provided":[72],"Wikipedia":[74],"articles.":[75],"Based":[76],"such":[78],"lists,":[79],"calculates":[81],"degree":[83],"between":[87],"two":[88,115],"words":[89],"through":[90],"cosine":[92],"measure.":[93],"The":[94],"proposed":[95],"solution":[96],"built":[98],"top":[100],"Hadoop":[103],"MapReduce":[104],"framework":[105],"Mahout":[108],"machine":[109],"learning":[110],"library.":[111],"Experimental":[112],"results":[113],"show":[114],"major":[116],"improvements":[117],"over":[118,190],"state":[120],"art,":[123],"particular":[125],"reference":[126,173],"Explicit":[129],"method.":[132],"First,":[133],"our":[134],"distributed":[135],"significantly":[137],"reduces":[138],"computation":[140],"time":[141],"build":[143],"vectors,":[146],"thus":[147],"enabling":[148],"use":[150],"larger":[152],"inputs":[153],"basis":[157],"more":[159],"accurate":[160],"results.":[161],"Second,":[162],"obtains":[164],"very":[166],"high":[167],"correlation":[168],"computed":[170],"benchmarks":[174],"derived":[175],"human":[177],"judgements.":[178],"Moreover,":[179],"its":[180],"accuracy":[181],"higher":[183],"than":[184],"solutions":[185],"reported":[186],"in":[187],"literature":[189],"multiple":[191],"benchmarks.":[192]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}