{"id":"https://openalex.org/W2612204738","doi":"https://doi.org/10.1145/3035918.3056443","title":"Synthesizing Extraction Rules from User Examples with SEER","display_name":"Synthesizing Extraction Rules from User Examples with SEER","publication_year":2017,"publication_date":"2017-05-09","ids":{"openalex":"https://openalex.org/W2612204738","doi":"https://doi.org/10.1145/3035918.3056443","mag":"2612204738"},"language":"en","primary_location":{"id":"doi:10.1145/3035918.3056443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3056443","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3056443&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3056443&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085409429","display_name":"Maeda F. Hanafi","orcid":"https://orcid.org/0009-0005-6663-2320"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maeda F. Hanafi","raw_affiliation_strings":["New York University - Abu Dhabi, Abu Dhabi, Uae"],"affiliations":[{"raw_affiliation_string":"New York University - Abu Dhabi, Abu Dhabi, Uae","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044418740","display_name":"Azza Abouzied","orcid":"https://orcid.org/0000-0003-4273-2536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azza Abouzied","raw_affiliation_strings":["New York University - Abu Dhabi, Abu Dhabi, Uae"],"affiliations":[{"raw_affiliation_string":"New York University - Abu Dhabi, Abu Dhabi, Uae","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050310059","display_name":"Laura Chiticariu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Chiticariu","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102944075","display_name":"Yunyao Li","orcid":"https://orcid.org/0009-0002-0814-4634"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085409429"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.487,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95985583,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1687","last_page":"1690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9965000152587891,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.7984746694564819},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7091991305351257},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6666169762611389},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.5641868710517883},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5585327744483948},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4694646894931793},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.43051767349243164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3867790699005127},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3865373134613037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.385918527841568},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3498784601688385},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2423863410949707},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1542026400566101},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08458498120307922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984746694564819},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7091991305351257},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6666169762611389},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.5641868710517883},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5585327744483948},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4694646894931793},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.43051767349243164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3867790699005127},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3865373134613037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385918527841568},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3498784601688385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2423863410949707},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1542026400566101},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08458498120307922},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3035918.3056443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3056443","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3056443&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3035918.3056443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3035918.3056443","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3056443&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G7101310381","display_name":null,"funder_award_id":"IIS-1420941","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2612204738.pdf","grobid_xml":"https://content.openalex.org/works/W2612204738.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1999563429","https://openalex.org/W2064766209","https://openalex.org/W2107391405","https://openalex.org/W2110367654","https://openalex.org/W2144416276","https://openalex.org/W2144951274","https://openalex.org/W2148317291","https://openalex.org/W2256286896","https://openalex.org/W2611907972"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W1981780420"],"abstract_inverted_index":{"Our":[0],"demonstration":[1],"showcases":[2],"SEER's":[3,59,92],"end-to-end":[4],"Information":[5],"Extraction":[6],"(IE)":[7],"workflow":[8,60],"where":[9],"users":[10,41,62],"highlight":[11],"texts":[12],"they":[13],"wish":[14],"to":[15,33,38,63,77],"extract.":[16],"Given":[17],"a":[18,73],"small":[19],"set":[20],"of":[21],"user-specified":[22],"example":[23],"extractions,":[24],"SEER":[25],"synthesizes":[26],"easy-to-understand":[27],"IE":[28,67],"rules":[29],"and":[30,95],"suggests":[31],"them":[32],"the":[34,45,50,66],"user.":[35],"In":[36],"addition":[37],"rule":[39,47,51,68,102],"suggestions,":[40],"can":[42],"quickly":[43],"pick":[44],"desired":[46],"by":[48,53,100],"filtering":[49],"suggestion":[52],"accepting":[54],"or":[55,86],"rejecting":[56],"proposed":[57],"extractions.":[58],"allows":[61],"jump":[64],"start":[65],"development":[69],"cycle;":[70],"it":[71],"is":[72],"less":[74],"time-consuming":[75],"alternative":[76],"machine":[78],"learning":[79,96],"methods":[80],"that":[81,89],"require":[82],"large":[83],"labeled":[84],"datasets":[85],"rule-based":[87],"approaches":[88],"are":[90,98],"labor-intensive.":[91],"design":[93],"principles":[94],"algorithm":[97],"motivated":[99],"how":[101],"developers":[103],"naturally":[104],"construct":[105],"data":[106],"extraction":[107],"rules.":[108]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}