{"id":"https://openalex.org/W2017368156","doi":"https://doi.org/10.1145/1854776.1854851","title":"Shortest path edit distance for detecting duplicate biological entities","display_name":"Shortest path edit distance for detecting duplicate biological entities","publication_year":2010,"publication_date":"2010-08-02","ids":{"openalex":"https://openalex.org/W2017368156","doi":"https://doi.org/10.1145/1854776.1854851","mag":"2017368156"},"language":"en","primary_location":{"id":"doi:10.1145/1854776.1854851","doi":"https://doi.org/10.1145/1854776.1854851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854776.1854851","pdf_url":null,"source":{"id":"https://openalex.org/S7407087958","display_name":"ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5065019593","display_name":"Alex Rudniy","orcid":"https://orcid.org/0000-0001-6008-3643","observed_orcids":["https://orcid.org/0000-0001-6008-3643"]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Rudniy","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045749444","display_name":"Min Song","orcid":"https://orcid.org/0000-0003-3255-1600","observed_orcids":["https://orcid.org/0000-0003-3255-1600","https://orcid.org/0000-0003-3893-3167"]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Song","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070654032","display_name":"James Geller","orcid":"https://orcid.org/0000-0002-9120-525X","observed_orcids":["https://orcid.org/0000-0002-9120-525X"]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Geller","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1287474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biological-data","display_name":"biological data","score":0.8349999785423279},{"id":"https://openalex.org/keywords/markov-random-fields","display_name":"Markov random fields","score":0.7139999866485596},{"id":"https://openalex.org/keywords/tf-idf","display_name":"TF-IDF","score":0.8500000238418579},{"id":"https://openalex.org/keywords/entity-deduplication","display_name":"entity deduplication","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8632041215896606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772660255432129},{"id":"https://openalex.org/C54385418","wikidata":"https://www.wikidata.org/wiki/Q2742711","display_name":"Distance","level":4,"score":0.7126671075820923},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.7047551870346069},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.5434049367904663},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5326295495033264},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4848078787326813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48441818356513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44535496830940247},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3831099271774292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38294517993927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34877902269363403},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34398213028907776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33718329668045044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17837300896644592},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.12698432803153992},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.12530171871185303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07917046546936035},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1854776.1854851","doi":"https://doi.org/10.1145/1854776.1854851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854776.1854851","pdf_url":null,"source":{"id":"https://openalex.org/S7407087958","display_name":"ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2812767486","display_name":null,"funder_award_id":"DUE-0434581DUE-0434998","funder_id":"https://openalex.org/F4320337408","funder_display_name":"Division of Undergraduate Education"},{"id":"https://openalex.org/G7119415825","display_name":"National Leadership Grants - Libraries \u2014 Foundation at New Jersey Institute of Technology (New Jersey Institute of Technology) (FY2004)","funder_award_id":"LG-02-04-0002-04","funder_id":"https://openalex.org/F4320306122","funder_display_name":"Institute of Museum and Library Services"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"},{"id":"https://openalex.org/F4320337408","display_name":"Division of Undergraduate Education","ror":"https://ror.org/02kd4km72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1646278814","https://openalex.org/W1970026646","https://openalex.org/W1992543256","https://openalex.org/W2039262760","https://openalex.org/W2068448872","https://openalex.org/W2074231493","https://openalex.org/W2074426357","https://openalex.org/W2076048958","https://openalex.org/W3123518987","https://openalex.org/W4240231372"],"related_works":["https://openalex.org/W2019096410","https://openalex.org/W2106302492","https://openalex.org/W2293561826","https://openalex.org/W2915154273","https://openalex.org/W7019271891","https://openalex.org/W2940926484","https://openalex.org/W4409317702","https://openalex.org/W1226029545","https://openalex.org/W4386952513","https://openalex.org/W2383458316"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,49],"novel":[4],"and":[5],"context-sensitive":[6],"Shortest":[7],"Path":[8],"Edit":[9,28],"Distance":[10],"(SPED)":[11],"applied":[12],"to":[13,37],"duplicate":[14],"entity":[15],"detection":[16],"in":[17,70],"biological":[18],"data.":[19],"SPED":[20,56,64],"is":[21],"an":[22],"extension":[23],"of":[24,40,48,63],"Markov":[25],"Random":[26],"Field-based":[27],"Distance.":[29],"It":[30],"transforms":[31],"the":[32,38,41,61],"edit":[33],"distance":[34],"computational":[35],"problem":[36],"calculation":[39],"shortest":[42],"path":[43],"among":[44],"two":[45],"selected":[46],"vertices":[47],"graph.":[50],"The":[51],"experimental":[52],"results":[53],"show":[54],"that":[55],"produces":[57],"competitive":[58],"outcomes.":[59],"SoftSPED,":[60],"combination":[62],"with":[65],"TFIDF,":[66],"achieves":[67],"superior":[68],"performance":[69],"most":[71],"cases.":[72]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
