{"id":"https://openalex.org/W4366327856","doi":"https://doi.org/10.1145/3555041.3589732","title":"DIALITE: Discover, Align and Integrate Open Data Tables","display_name":"DIALITE: Discover, Align and Integrate Open Data Tables","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4366327856","doi":"https://doi.org/10.1145/3555041.3589732"},"language":"en","primary_location":{"id":"doi:10.1145/3555041.3589732","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.08285","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047161025","display_name":"Aamod Khatiwada","orcid":"https://orcid.org/0000-0001-5720-1207"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aamod Khatiwada","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5720-1207","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002899918","display_name":"Roee Shraga","orcid":"https://orcid.org/0000-0001-8803-8481"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roee Shraga","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8803-8481","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1484-4787","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047161025"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.9862,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7729964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8425965309143066},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8290470838546753},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7498452067375183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4832954704761505},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4483918249607086},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.412495493888855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3990713357925415},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13003069162368774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425965309143066},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8290470838546753},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7498452067375183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4832954704761505},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4483918249607086},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.412495493888855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3990713357925415},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13003069162368774}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3555041.3589732","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.08285","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.08285","pdf_url":"https://arxiv.org/pdf/2304.08285","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.08285","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.08285","pdf_url":"https://arxiv.org/pdf/2304.08285","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1537211332","display_name":null,"funder_award_id":"IIS-1956096","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G601730711","display_name":"III : Medium: Collaborative Research: From Open Data to Open Data Curation","funder_award_id":"2107248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6745713617","display_name":null,"funder_award_id":"1956096","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366327856.pdf","grobid_xml":"https://content.openalex.org/works/W4366327856.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2082055368","https://openalex.org/W2108940005","https://openalex.org/W2440178963","https://openalex.org/W2798664493","https://openalex.org/W2948163032","https://openalex.org/W2961334167","https://openalex.org/W2963174348","https://openalex.org/W3013082216","https://openalex.org/W3034944976","https://openalex.org/W3095319910","https://openalex.org/W3149201378","https://openalex.org/W3196904276","https://openalex.org/W4321448337","https://openalex.org/W4380433117"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W4394193569","https://openalex.org/W1797990060","https://openalex.org/W4232484699","https://openalex.org/W2126703991","https://openalex.org/W2610897791"],"abstract_inverted_index":{"We":[0],"demonstrate":[1],"a":[2],"novel":[3],"table":[4,38],"discovery":[5,39,82],"pipeline":[6,69],"called":[7],"DIALITE":[8,20,42],"that":[9,73],"allows":[10,27,54],"users":[11,28,55],"to":[12,29,47,56],"discover,":[13],"integrate":[14],"and":[15,79,83],"analyze":[16,57],"open":[17,33],"data":[18,34],"tables.":[19],"has":[21],"three":[22],"main":[23],"stages.":[24],"First,":[25],"it":[26,53],"discover":[30],"tables":[31,46],"from":[32],"platforms":[35],"using":[36],"state-of-the-art":[37],"techniques.":[40],"Second,":[41],"integrates":[43],"the":[44,58,74],"discovered":[45],"produce":[48],"an":[49],"integrated":[50],"table.":[51],"Finally,":[52],"integration":[59,84],"result":[60],"by":[61],"applying":[62],"different":[63],"downstreaming":[64],"tasks":[65],"over":[66],"it.":[67],"Our":[68],"is":[70],"flexible":[71],"such":[72],"user":[75],"can":[76],"easily":[77],"add":[78],"compare":[80],"additional":[81],"algorithms.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
