{"id":"https://openalex.org/W2976890275","doi":"https://doi.org/10.1145/3341981.3344248","title":"SearchIE","display_name":"SearchIE","publication_year":2019,"publication_date":"2019-09-26","ids":{"openalex":"https://openalex.org/W2976890275","doi":"https://doi.org/10.1145/3341981.3344248","mag":"2976890275"},"language":"en","primary_location":{"id":"doi:10.1145/3341981.3344248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344248","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089659476","display_name":"Sheikh Muhammad Sarwar","orcid":"https://orcid.org/0000-0003-4820-9201"},"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":true,"raw_author_name":"Sheikh Muhammad Sarwar","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"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":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089659476"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.0311,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79981291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"200","issue":null,"first_page":"249","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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":0.8688443899154663},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5506830811500549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749605655670166},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.47213345766067505},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44358253479003906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3398667871952057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8688443899154663},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5506830811500549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749605655670166},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47213345766067505},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44358253479003906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3398667871952057}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341981.3344248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3341981.3344248","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341981.3344248","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341981.3344248","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G8318576999","display_name":null,"funder_award_id":"IIS-1617408","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9890268","display_name":"III: Small: Interactive Construction of Complex Query Models","funder_award_id":"1617408","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/W2976890275.pdf","grobid_xml":"https://content.openalex.org/works/W2976890275.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W35034236","https://openalex.org/W2009312133","https://openalex.org/W2051940813","https://openalex.org/W2093390569","https://openalex.org/W2109378394","https://openalex.org/W2117473841","https://openalex.org/W2252062548","https://openalex.org/W2741804652","https://openalex.org/W2963229139","https://openalex.org/W3104154399","https://openalex.org/W4206765718"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3136979370","https://openalex.org/W4387849428","https://openalex.org/W2058170566"],"abstract_inverted_index":{"We":[0,145],"address":[1,13],"the":[2],"problem":[3],"of":[4,25,32,71,116],"entity":[5],"extraction":[6,21],"with":[7,15,47,64,141,165],"a":[8,29,43,50,55,68,91,104,114,136,167],"very":[9],"few":[10],"examples":[11],"and":[12,59,118],"it":[14,152],"an":[16],"information":[17],"retrieval":[18],"approach.":[19],"Existing":[20],"approaches":[22],"consider":[23],"millions":[24],"features":[26],"extracted":[27],"from":[28,135],"large":[30],"number":[31],"training":[33,84],"data":[34,38,67,106],"cases.":[35],"Typically,":[36],"these":[37],"cases":[39],"are":[40,61],"generated":[41],"by":[42,149,161],"distant":[44],"supervision":[45],"approach":[46,120],"entities":[48,60,73],"in":[49,102],"knowledge":[51],"base.":[52],"After":[53],"that":[54,121,151],"model":[56,139],"is":[57,90],"learned":[58],"extracted.":[62],"However,":[63],"extremely":[65,142],"limited":[66,105,143],"ranked":[69,95],"list":[70,96],"relevant":[72],"can":[74],"be":[75],"helpful":[76],"to":[77,81,157],"obtain":[78],"user":[79],"feedback":[80],"get":[82],"more":[83],"data.":[85,144],"As":[86],"Information":[87],"Retrieval":[88],"(IR)":[89],"natural":[92],"choice":[93],"for":[94],"generation,":[97],"we":[98,111],"explore":[99,146],"its":[100],"effectiveness":[101],"such":[103],"case.":[107],"To":[108],"this":[109],"end,":[110],"propose":[112],"SearchIE,":[113],"hybrid":[115],"IR":[117],"NLP":[119,127,155],"indexes":[122],"documents":[123],"represented":[124],"using":[125],"handcrafted":[126],"features.":[128],"At":[129],"query":[130],"time":[131],"SearchIE":[132],"samples":[133],"terms":[134],"Logistic":[137],"Regression":[138],"trained":[140],"SearchIE's":[147],"potential":[148],"showing":[150],"supersedes":[153],"state-of-the-art":[154],"models":[156],"find":[158],"civilians":[159],"killed":[160],"US":[162],"police":[163],"officers":[164],"only":[166],"single":[168],"civilian":[169],"name":[170],"as":[171],"example.":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-10-03T00:00:00"}