{"id":"https://openalex.org/W4389609822","doi":"https://doi.org/10.1145/3626766","title":"Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation","display_name":"Watchog: A Light-weight Contrastive Learning based Framework for Column Annotation","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389609822","doi":"https://doi.org/10.1145/3626766"},"language":"en","primary_location":{"id":"doi:10.1145/3626766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626766","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-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/A5087858861","display_name":"Zhengjie Miao","orcid":"https://orcid.org/0009-0008-2371-1186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengjie Miao","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-2371-1186","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346150","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0002-3172-6133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3172-6133","affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2221,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88739618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"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":0.9993000030517578,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9779000282287598,"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/computer-science","display_name":"Computer science","score":0.788583517074585},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7113879919052124},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.6555304527282715},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6082757115364075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5511476993560791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5149415135383606},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4522819519042969},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4224420487880707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4223291873931885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3567420542240143},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35085850954055786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788583517074585},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7113879919052124},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.6555304527282715},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6082757115364075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511476993560791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5149415135383606},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4522819519042969},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4224420487880707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4223291873931885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3567420542240143},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35085850954055786},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626766","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2255747889","https://openalex.org/W2341748398","https://openalex.org/W2522154031","https://openalex.org/W2740592503","https://openalex.org/W2952479794","https://openalex.org/W2962739339","https://openalex.org/W2971470875","https://openalex.org/W3005680577","https://openalex.org/W3017293324","https://openalex.org/W3082424964","https://openalex.org/W3102616888","https://openalex.org/W3134652006","https://openalex.org/W3162752841","https://openalex.org/W3165753548","https://openalex.org/W3166417463","https://openalex.org/W3168052339","https://openalex.org/W3174036215","https://openalex.org/W3198440572","https://openalex.org/W4205922070","https://openalex.org/W4221163895","https://openalex.org/W4281396256","https://openalex.org/W4310390625","https://openalex.org/W4312905556","https://openalex.org/W4375928372","https://openalex.org/W4379390735","https://openalex.org/W4383051975","https://openalex.org/W6692289000","https://openalex.org/W6727648789","https://openalex.org/W6788399295","https://openalex.org/W6848046949"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W3123448197","https://openalex.org/W1510114644"],"abstract_inverted_index":{"Relational":[0],"Web":[1],"tables":[2,98],"provide":[3],"valuable":[4],"resources":[5],"for":[6,97,130,141],"numerous":[7],"downstream":[8,131],"applications,":[9],"making":[10],"table":[11,41,104,114],"understanding,":[12],"especially":[13],"column":[14,132,159],"annotation":[15,133,160],"that":[16],"identifies":[17],"semantic":[18,208],"types":[19],"and":[20,58,195,199],"relations":[21],"of":[22,30,47,153,207],"columns,":[23],"a":[24,101,178],"hot":[25],"topic":[26],"in":[27,40,127,157,197],"the":[28,45,67,73,85,112,151,172,183,188,205],"field":[29],"data":[31,68,75],"management.":[32],"Despite":[33],"recent":[34],"efforts":[35],"to":[36,72,93,116,193],"improve":[37],"different":[38,78,163],"tasks":[39,161],"understanding":[42],"by":[43,99,177,191],"using":[44],"power":[46],"large":[48],"pre-trained":[49],"language":[50],"models,":[51],"existing":[52],"methods":[53],"heavily":[54],"rely":[55],"on":[56,146,204],"large-scale":[57,102],"high-quality":[59],"labeled":[60,124],"instances,":[61],"while":[62],"they":[63],"still":[64],"suffer":[65],"from":[66],"sparsity":[69],"problem":[70],"due":[71],"imbalanced":[74],"distribution":[76],"among":[77],"classes.":[79],"In":[80,165,182],"this":[81],"paper,":[82],"we":[83,136],"propose":[84],"Watchog":[86,168,186],"framework,":[87],"which":[88],"employs":[89],"contrastive":[90],"learning":[91],"techniques":[92,140,156],"learn":[94],"robust":[95],"representations":[96,115],"leveraging":[100],"unlabeled":[103],"corpus":[105],"with":[106,120],"minimal":[107],"overhead.":[108],"Our":[109],"approach":[110],"enables":[111],"learned":[113],"enhance":[117],"fine":[118],"tuning":[119],"much":[121],"fewer":[122],"additional":[123],"instances":[125],"than":[126],"prior":[128],"studies":[129],"tasks.":[134],"Besides,":[135],"further":[137],"proposed":[138,155],"optimization":[139],"semi-supervised":[142,184],"settings.":[143,164],"Experimental":[144],"results":[145],"popular":[147],"benchmarking":[148],"datasets":[149],"illustrate":[150],"superiority":[152],"our":[154,167],"two":[158],"under":[162],"particular,":[166],"framework":[169],"effectively":[170],"alleviates":[171],"class":[173],"imbalance":[174],"issue":[175],"caused":[176],"long-tailed":[179],"label":[180],"distribution.":[181],"setting,":[185],"outperforms":[187],"best-known":[189],"method":[190],"up":[192],"26%":[194],"41%":[196],"Micro":[198],"Macro":[200],"F1":[201],"scores,":[202],"respectively,":[203],"task":[206],"type":[209],"detection.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}