{"id":"https://openalex.org/W3169442836","doi":"https://doi.org/10.1145/3448016.3457334","title":"Adaptive Rule Discovery for Labeling Text Data","display_name":"Adaptive Rule Discovery for Labeling Text Data","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3169442836","doi":"https://doi.org/10.1145/3448016.3457334","mag":"3169442836"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018077979","display_name":"Behzad Golshan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Behzad Golshan","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026007789","display_name":"Wang-Chiew Tan","orcid":"https://orcid.org/0009-0008-4174-7545"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Chiew Tan","raw_affiliation_strings":["Facebook AI, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2217","last_page":"2225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/bottleneck","display_name":"Bottleneck","score":0.8243226408958435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8223133087158203},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5995987057685852},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5573576092720032},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4866064786911011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48264509439468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47000962495803833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46367642283439636},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4504481554031372},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.424038827419281},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09313905239105225}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8243226408958435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223133087158203},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5995987057685852},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5573576092720032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4866064786911011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48264509439468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47000962495803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46367642283439636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4504481554031372},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.424038827419281},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09313905239105225},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448016.3457334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1483236033","https://openalex.org/W1541280084","https://openalex.org/W1832693441","https://openalex.org/W1889268436","https://openalex.org/W1988560072","https://openalex.org/W2068737686","https://openalex.org/W2117173982","https://openalex.org/W2142086811","https://openalex.org/W2253491900","https://openalex.org/W2612972698","https://openalex.org/W2613881683","https://openalex.org/W2725395424","https://openalex.org/W2753688405","https://openalex.org/W2799106927","https://openalex.org/W2896587760","https://openalex.org/W2898956098","https://openalex.org/W2917458986","https://openalex.org/W2950873798","https://openalex.org/W3032015135","https://openalex.org/W3137039868","https://openalex.org/W6682171051","https://openalex.org/W6750130407"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Creating":[0],"and":[1,15,88,105],"collecting":[2],"labeled":[3,68,97],"data":[4,62,72,101],"is":[5],"one":[6],"of":[7,18,32,56,70,81,99],"the":[8,16,38,71,92,100],"major":[9],"bottlenecks":[10],"in":[11,108],"machine":[12],"learning":[13],"pipelines":[14],"emergence":[17],"automated":[19],"feature":[20],"generation":[21],"techniques":[22,42],"such":[23],"as":[24],"deep":[25],"learning,":[26],"which":[27],"typically":[28],"requires":[29],"a":[30,54,67,96],"lot":[31],"training":[33],"data,":[34],"has":[35],"further":[36],"exacerbated":[37],"problem.":[39],"While":[40],"weak-supervision":[41],"have":[43],"circumvented":[44],"this":[45],"bottleneck,":[46],"existing":[47],"frameworks":[48],"either":[49],"require":[50,66],"users":[51],"to":[52,60,73],"write":[53],"set":[55],"diverse,":[57],"high-quality":[58],"rules":[59,76,84],"label":[61],"(e.g.,":[63,77],"Snorkel),":[64],"or":[65],"subset":[69,98],"automatically":[74],"mine":[75],"Snuba).":[78],"The":[79],"process":[80],"manually":[82],"writing":[83],"can":[85,102],"be":[86,103],"tedious":[87],"time":[89],"consuming.":[90],"At":[91],"same":[93],"time,":[94],"creating":[95],"costly":[104],"even":[106],"infeasible":[107],"imbalanced":[109],"settings.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}