{"id":"https://openalex.org/W2099276606","doi":"https://doi.org/10.1109/icdm.2003.1250998","title":"Mining the Web to discover the meanings of an ambiguous word","display_name":"Mining the Web to discover the meanings of an ambiguous word","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2099276606","doi":"https://doi.org/10.1109/icdm.2003.1250998","mag":"2099276606"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-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/A5060776040","display_name":"Raz Tamir","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"R. Tamir","raw_affiliation_strings":["Hebrew University of Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049674705","display_name":"Reinhard Rapp","orcid":"https://orcid.org/0000-0002-7245-551X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"R. Rapp","raw_affiliation_strings":["Johannes Gutenberg Universit\u00e4t Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg Universit\u00e4t Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060776040"],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":1.7988,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87488013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"34","issue":null,"first_page":"645","last_page":"648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9975000023841858,"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/word","display_name":"Word (group theory)","score":0.7967850565910339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7427383661270142},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.6551473140716553},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.654747724533081},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"Word-sense disambiguation","score":0.6439653635025024},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5628026723861694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5471545457839966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4888293147087097},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4775315523147583},{"id":"https://openalex.org/keywords/word-association","display_name":"Word Association","score":0.467360258102417},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.46409574151039124},{"id":"https://openalex.org/keywords/polysemy","display_name":"Polysemy","score":0.45097512006759644},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4351062774658203},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.41850727796554565},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3129770755767822},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1553116738796234},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11239022016525269},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.10716694593429565}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7967850565910339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427383661270142},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.6551473140716553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.654747724533081},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.6439653635025024},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5628026723861694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5471545457839966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4888293147087097},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4775315523147583},{"id":"https://openalex.org/C2777974174","wikidata":"https://www.wikidata.org/wiki/Q744875","display_name":"Word Association","level":2,"score":0.467360258102417},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.46409574151039124},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.45097512006759644},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4351062774658203},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.41850727796554565},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3129770755767822},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1553116738796234},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11239022016525269},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.10716694593429565},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2003.1250998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W2012156767","https://openalex.org/W2050712820","https://openalex.org/W2101210369","https://openalex.org/W4206165639","https://openalex.org/W4238346259"],"related_works":["https://openalex.org/W2089001890","https://openalex.org/W2173076481","https://openalex.org/W2101293500","https://openalex.org/W2384058382","https://openalex.org/W2000205775","https://openalex.org/W1998827703","https://openalex.org/W2124313972","https://openalex.org/W2251529656","https://openalex.org/W2324822715","https://openalex.org/W2330879361"],"abstract_inverted_index":{"In":[0],"information":[1,6],"retrieval":[2],"and":[3,143],"text":[4],"mining,":[5],"on":[7,52],"word":[8,30,56,73],"senses":[9,69],"is":[10,50,66,100,108,140],"usually":[11],"taken":[12],"from":[13,60,156],"dictionaries":[14],"or":[15],"lexical":[16],"databases":[17],"that":[18,67,116],"have":[19],"been":[20],"prepared":[21],"by":[22,77],"lexicographers.":[23],"We":[24],"propose":[25],"an":[26,71,128],"automatic":[27],"method":[28],"for":[29,34,122,132],"sense":[31,41,124],"induction,":[32],"i.e.":[33,91],"the":[35,53,68,96,118,147,157,173],"discovery":[36],"of":[37,40,55,70,134,150,166],"a":[38,44,82,111,164],"set":[39],"descriptors":[42],"to":[43,85,127,171],"given":[45],"ambiguous":[46,72,167],"word.":[47],"The":[48,63,137],"approach":[49,115,139],"based":[51,109],"statistics":[54],"co-occurrence":[57,120,130],"as":[58,101,103,152],"derived":[59],"Web":[61,98],"pages.":[62],"underlying":[64],"assumption":[65],"are":[74,88,161],"best":[75],"described":[76],"terms":[78],"that,":[79],"although":[80],"bearing":[81],"strong":[83],"association":[84,93,106],"this":[86],"word,":[87],"mutually":[89],"exclusive,":[90],"whose":[92],"strength":[94,107],"within":[95],"retrieved":[97],"pages":[99],"weak":[102],"possible.":[104],"Measuring":[105],"upon":[110],"novel":[112],"confidence":[113],"gain":[114],"relates":[117],"observed":[119],"frequency":[121,131],"two":[123],"descriptor":[125],"candidates":[126],"average":[129],"pairs":[133],"arbitrary":[135],"words.":[136],"proposed":[138],"fully":[141],"unsupervised":[142],"takes":[144],"into":[145],"account":[146],"contemporary":[148],"meanings":[149],"words,":[151],"reflected":[153],"in":[154,172],"texts":[155],"Internet.":[158],"Our":[159],"results":[160],"evaluated":[162],"using":[163],"list":[165],"words":[168],"commonly":[169],"referred":[170],"literature.":[174]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
