{"id":"https://openalex.org/W2947774097","doi":"https://doi.org/10.1145/3314221.3322485","title":"Synthesis and machine learning for heterogeneous extraction","display_name":"Synthesis and machine learning for heterogeneous extraction","publication_year":2019,"publication_date":"2019-06-07","ids":{"openalex":"https://openalex.org/W2947774097","doi":"https://doi.org/10.1145/3314221.3322485","mag":"2947774097"},"language":"en","primary_location":{"id":"doi:10.1145/3314221.3322485","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314221.3322485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-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/A5090842155","display_name":"Arun Iyer","orcid":"https://orcid.org/0000-0001-7377-7599"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arun Iyer","raw_affiliation_strings":["Microsoft Research, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079189408","display_name":"Manohar Jonnalagedda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manohar Jonnalagedda","raw_affiliation_strings":["Inpher, Switzerland"],"affiliations":[{"raw_affiliation_string":"Inpher, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102483404","display_name":"Suresh Parthasarathy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh Parthasarathy","raw_affiliation_strings":["Microsoft Research, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000188805","display_name":"Arjun Radhakrishna","orcid":"https://orcid.org/0000-0002-5559-5932"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Radhakrishna","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076139746","display_name":"Sriram K. Rajamani","orcid":"https://orcid.org/0000-0002-1400-7065"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram K. Rajamani","raw_affiliation_strings":["Microsoft Research, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090842155"],"corresponding_institution_ids":["https://openalex.org/I4210124949"],"apc_list":null,"apc_paid":null,"fwci":5.0873,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95670358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9886999726295471,"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":0.8278931379318237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5652757883071899},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5625593066215515},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.55503910779953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039293169975281},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4728924334049225},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45632174611091614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37658464908599854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35560792684555054},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2648985981941223},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07918810844421387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278931379318237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5652757883071899},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5625593066215515},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.55503910779953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039293169975281},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4728924334049225},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45632174611091614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37658464908599854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35560792684555054},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2648985981941223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07918810844421387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3314221.3322485","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3314221.3322485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1034915372","https://openalex.org/W1507894341","https://openalex.org/W1912569824","https://openalex.org/W1980176056","https://openalex.org/W2060610732","https://openalex.org/W2064675550","https://openalex.org/W2065568440","https://openalex.org/W2070090726","https://openalex.org/W2080132606","https://openalex.org/W2101234009","https://openalex.org/W2132525863","https://openalex.org/W2135479443","https://openalex.org/W2144951274","https://openalex.org/W2145600026","https://openalex.org/W2147880316","https://openalex.org/W2238673293","https://openalex.org/W2296283641","https://openalex.org/W2560674852","https://openalex.org/W2601273560","https://openalex.org/W2603456259","https://openalex.org/W2785774944","https://openalex.org/W2913389685","https://openalex.org/W2937192905","https://openalex.org/W2963319332","https://openalex.org/W2964057329","https://openalex.org/W2997591727","https://openalex.org/W3003266211","https://openalex.org/W3015882749","https://openalex.org/W3121841058","https://openalex.org/W4237412827"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W3112355890","https://openalex.org/W2613685774","https://openalex.org/W4220741973","https://openalex.org/W2961085424","https://openalex.org/W2326464900","https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W2594414941"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,49],"way":[3],"to":[4,15,47],"combine":[5],"techniques":[6],"from":[7,19,32,38,41,54],"the":[8],"program":[9],"synthesis":[10],"and":[11],"machine":[12],"learning":[13],"communities":[14],"extract":[16,48],"structured":[17,52],"information":[18],"heterogeneous":[20],"data.":[21,56],"Such":[22],"problems":[23],"arise":[24],"in":[25],"several":[26],"situations":[27],"such":[28,55],"as":[29],"extracting":[30],"attributes":[31,53],"web":[33],"pages,":[34],"machine-generated":[35],"emails,":[36],"or":[37],"data":[39],"obtained":[40],"multiple":[42],"sources.":[43],"Our":[44],"goal":[45],"is":[46],"set":[50],"of":[51]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}