{"id":"https://openalex.org/W3083092543","doi":"https://doi.org/10.1145/3409256.3409811","title":"Learning to Rank Entities for Set Expansion from Unstructured Data","display_name":"Learning to Rank Entities for Set Expansion from Unstructured Data","publication_year":2020,"publication_date":"2020-09-05","ids":{"openalex":"https://openalex.org/W3083092543","doi":"https://doi.org/10.1145/3409256.3409811","mag":"3083092543"},"language":"en","primary_location":{"id":"doi:10.1145/3409256.3409811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","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/A5090488104","display_name":"Puxuan Yu","orcid":"https://orcid.org/0000-0001-7913-8632"},"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":"Puxuan Yu","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":"middle","author":{"id":"https://openalex.org/A5103185916","display_name":"Razieh Rahimi","orcid":"https://orcid.org/0000-0002-2584-3309"},"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":"Razieh Rahimi","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":"middle","author":{"id":"https://openalex.org/A5090589471","display_name":"Zhiqi Huang","orcid":"https://orcid.org/0000-0002-1506-1063"},"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":"Zhiqi Huang","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":4,"corresponding_author_ids":["https://openalex.org/A5090488104"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78506385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8483139276504517},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6758983135223389},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.672650933265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574589192867279},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5661438703536987},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5657188892364502},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5291004180908203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5089194774627686},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5083009600639343},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4779624938964844},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.476166695356369},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47300297021865845},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45347148180007935},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.44054776430130005},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.42383643984794617},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4151000380516052},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.28351593017578125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2627905011177063},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.11342450976371765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483139276504517},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6758983135223389},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.672650933265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574589192867279},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5661438703536987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5657188892364502},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5291004180908203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5089194774627686},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5083009600639343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4779624938964844},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.476166695356369},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47300297021865845},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45347148180007935},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.44054776430130005},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.42383643984794617},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4151000380516052},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.28351593017578125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2627905011177063},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.11342450976371765},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3409256.3409811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3409256.3409811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1555486317","https://openalex.org/W1593045043","https://openalex.org/W1975879668","https://openalex.org/W1978400666","https://openalex.org/W1982242209","https://openalex.org/W2009510620","https://openalex.org/W2024264062","https://openalex.org/W2026810221","https://openalex.org/W2035432878","https://openalex.org/W2108862644","https://openalex.org/W2114867936","https://openalex.org/W2118356981","https://openalex.org/W2128407051","https://openalex.org/W2133108446","https://openalex.org/W2142537246","https://openalex.org/W2161669948","https://openalex.org/W2171743956","https://openalex.org/W2171956623","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2251130204","https://openalex.org/W2260244612","https://openalex.org/W2293997450","https://openalex.org/W2295058825","https://openalex.org/W2593560537","https://openalex.org/W2740452428","https://openalex.org/W2753798143","https://openalex.org/W2777203405","https://openalex.org/W2809189384","https://openalex.org/W2882319491","https://openalex.org/W2886258473","https://openalex.org/W2888813492","https://openalex.org/W2950133940","https://openalex.org/W2962739339","https://openalex.org/W2962762512","https://openalex.org/W2963341956","https://openalex.org/W2963893058","https://openalex.org/W2964023183","https://openalex.org/W2970427399","https://openalex.org/W2980282514","https://openalex.org/W3004011066","https://openalex.org/W3035458998","https://openalex.org/W3102679845"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W3000685722","https://openalex.org/W4255258373","https://openalex.org/W2032007337","https://openalex.org/W1884363728","https://openalex.org/W4253099099","https://openalex.org/W4386977977","https://openalex.org/W4200491110","https://openalex.org/W4313162113"],"abstract_inverted_index":{"We":[0,34,88],"propose":[1],"using":[2],"learning-to-rank":[3],"for":[4,70,112],"entity":[5,50,53,57,79,96],"set":[6,25,30,58],"expansion":[7,59],"(ESE)":[8],"from":[9,23,98,123,148],"unstructured":[10],"data,":[11],"the":[12,24,65,74,83,145,149],"task":[13],"of":[14,31,49,76,85,108,120,134],"finding":[15],"\"sibling\"":[16],"entities":[17],"within":[18],"a":[19,28,36,91,99,105],"corpus":[20],"that":[21,42,93,127,144],"are":[22],"characterized":[26],"by":[27],"small":[29],"seed":[32],"entities.":[33],"present":[35],"two-channel":[37],"neural":[38,86,113],"re-ranking":[39],"model,":[40],"NESE,":[41],"jointly":[43],"learns":[44],"exact":[45],"and":[46,67,136],"semantic":[47],"matching":[48],"contexts":[51],"through":[52,140],"interaction":[54],"features.":[55],"Although":[56],"has":[60,81],"drawn":[61],"increasing":[62],"attention":[63],"in":[64,132],"IR":[66],"NLP":[68],"communities":[69],"its":[71],"various":[72],"applications,":[73],"lack":[75],"massive":[77],"annotated":[78],"sets":[80,97],"hindered":[82],"development":[84],"approaches.":[87],"describe":[89],"DBpedia-Sets,":[90],"toolkit":[92],"automatically":[94],"extracts":[95],"plain":[100],"text":[101],"collection,":[102],"thus":[103],"providing":[104],"large":[106],"amount":[107],"distant":[109],"supervision":[110],"data":[111,151],"model":[114],"training.":[115],"Experiments":[116],"on":[117],"real":[118],"datasets":[119],"different":[121,124],"scales":[122],"domains":[125],"show":[126],"NESE":[128],"outperforms":[129],"state-of-the-art":[130],"approaches":[131],"terms":[133],"precision":[135],"MAP.":[137],"Furthermore,":[138],"evaluation":[139],"human":[141],"annotations":[142],"shows":[143],"knowledge":[146],"learned":[147],"training":[150],"is":[152],"generalizable.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}