{"id":"https://openalex.org/W2095719843","doi":"https://doi.org/10.1109/icdim.2007.4444195","title":"Discovering interchangeable words from string databases","display_name":"Discovering interchangeable words from string databases","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2095719843","doi":"https://doi.org/10.1109/icdim.2007.4444195","mag":"2095719843"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2007.4444195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","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/A5046665875","display_name":"Marco \u00c1lvarez","orcid":"https://orcid.org/0000-0002-8528-5089"},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marco A. Alvarez","raw_affiliation_strings":["Department of Computer Science, Utah State University, Logan, UT, USA","Dept. of Comput. Sci., Utah State Univ., Logan, UT"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, UT, USA","institution_ids":["https://openalex.org/I121980950"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Utah State Univ., Logan, UT","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109219199","display_name":"SeungJin Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I121980950","display_name":"Utah State University","ror":"https://ror.org/00h6set76","country_code":"US","type":"education","lineage":["https://openalex.org/I121980950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"SeungJin Lim","raw_affiliation_strings":["Department of Computer Science, Utah State University, Logan, UT, USA","Dept. of Comput. Sci., Utah State Univ., Logan, UT"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Utah State University, Logan, UT, USA","institution_ids":["https://openalex.org/I121980950"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Utah State Univ., Logan, UT","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046665875"],"corresponding_institution_ids":["https://openalex.org/I121980950"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.16944604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"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/interchangeability","display_name":"Interchangeability","score":0.845786452293396},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.7182446122169495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6898834705352783},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6863782405853271},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6044032573699951},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5560784935951233},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5410948395729065},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.524848461151123},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5133015513420105},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4641614556312561},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.44795548915863037},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44370660185813904},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44212955236434937},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.4177919626235962},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4006364643573761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38538211584091187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3798646628856659},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33869439363479614},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.23447731137275696},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22783538699150085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21336498856544495},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.16392377018928528},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10563820600509644},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.07952526211738586}],"concepts":[{"id":"https://openalex.org/C2779606619","wikidata":"https://www.wikidata.org/wiki/Q17092524","display_name":"Interchangeability","level":2,"score":0.845786452293396},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.7182446122169495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898834705352783},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6863782405853271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6044032573699951},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5560784935951233},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5410948395729065},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.524848461151123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5133015513420105},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4641614556312561},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.44795548915863037},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44370660185813904},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44212955236434937},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.4177919626235962},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4006364643573761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38538211584091187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3798646628856659},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33869439363479614},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.23447731137275696},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22783538699150085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21336498856544495},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.16392377018928528},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10563820600509644},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.07952526211738586},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1109/icdim.2007.4444195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2007.4444195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 2nd International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1573498319","https://openalex.org/W1647671624","https://openalex.org/W1647729745","https://openalex.org/W1959533457","https://openalex.org/W2038721957","https://openalex.org/W2087739686","https://openalex.org/W2100935296","https://openalex.org/W2115792525","https://openalex.org/W2117805756","https://openalex.org/W2123457740","https://openalex.org/W2136480620","https://openalex.org/W2140887277","https://openalex.org/W2534712034","https://openalex.org/W2950225692","https://openalex.org/W2962689487","https://openalex.org/W4213168938","https://openalex.org/W4214751380","https://openalex.org/W4235505822","https://openalex.org/W6601044945","https://openalex.org/W6634395915","https://openalex.org/W6636915900","https://openalex.org/W6636975626","https://openalex.org/W6640984990","https://openalex.org/W6675339850","https://openalex.org/W6677712588","https://openalex.org/W6681340555"],"related_works":["https://openalex.org/W2461708070","https://openalex.org/W2950268498","https://openalex.org/W1505906253","https://openalex.org/W2102443632","https://openalex.org/W4280559639","https://openalex.org/W4285090010","https://openalex.org/W1597110170","https://openalex.org/W2575897682","https://openalex.org/W2788104449","https://openalex.org/W4362583275"],"abstract_inverted_index":{"This":[0],"paper":[1,97],"presents":[2],"a":[3,101],"solution":[4,93],"for":[5,49,79,104],"the":[6,13,61,66,77,83,89,108],"problem":[7],"of":[8,15,19,44,60,63,69,74],"finding":[9],"interchangeable":[10,45],"words":[11,22,24,75],"in":[12,30,82,95],"context":[14],"an":[16],"input":[17,90],"collection":[18],"strings.":[20],"Interchangeable":[21],"are":[23],"that":[25],"can":[26],"be":[27,47],"replaced":[28],"indistinctly":[29],"phrases":[31],"or":[32],"free":[33],"text":[34],"without":[35],"deviating":[36],"its":[37],"actual":[38],"meaning.":[39],"Under":[40],"restricted":[41],"conditions,":[42],"pairs":[43,73,81,106],"might":[46],"useful":[48],"data":[50],"deduplication,":[51],"copy":[52],"detection,":[53],"software":[54],"localization,":[55],"among":[56],"others.":[57],"The":[58,92],"calculation":[59,68],"degree":[62],"interchangeability":[64],"involves":[65],"accurate":[67],"semantic":[70],"similarity":[71],"between":[72],"and":[76],"search":[78,85,102],"candidate":[80,105],"overall":[84],"space":[86],"imposed":[87],"by":[88,100],"collection.":[91],"presented":[94],"this":[96],"is":[98],"composed":[99],"method":[103],"using":[107],"Levenshtein":[109],"distance":[110],"algorithm":[111]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
