{"id":"https://openalex.org/W2962762512","doi":"https://doi.org/10.1145/3331184.3331359","title":"Corpus-based Set Expansion with Lexical Features and Distributed Representations","display_name":"Corpus-based Set Expansion with Lexical Features and Distributed Representations","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W2962762512","doi":"https://doi.org/10.1145/3331184.3331359","mag":"2962762512"},"language":"en","primary_location":{"id":"doi:10.1145/3331184.3331359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","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/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":false,"raw_author_name":"Puxuan Yu","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/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"],"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/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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.6401,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88492304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1153","last_page":"1156"},"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9973000288009644,"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":0.8189377784729004},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7112952470779419},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6727332472801208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6175414323806763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6130614876747131},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6063400506973267},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5922373533248901},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.4597937762737274},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36175596714019775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07679155468940735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189377784729004},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7112952470779419},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6727332472801208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6175414323806763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6130614876747131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6063400506973267},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5922373533248901},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.4597937762737274},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36175596714019775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07679155468940735},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3331184.3331359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1595923458","https://openalex.org/W1958239248","https://openalex.org/W1982242209","https://openalex.org/W2009510620","https://openalex.org/W2035432878","https://openalex.org/W2133108446","https://openalex.org/W2134489415","https://openalex.org/W2150815390","https://openalex.org/W2155061451","https://openalex.org/W2161669948","https://openalex.org/W2171743956","https://openalex.org/W2260244612","https://openalex.org/W2284650288","https://openalex.org/W2293997450","https://openalex.org/W2295058825","https://openalex.org/W2777203405","https://openalex.org/W2809189384","https://openalex.org/W2882319491","https://openalex.org/W2883942403","https://openalex.org/W2950133940","https://openalex.org/W2963341956"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2794488505","https://openalex.org/W4301594054","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W4386392971","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W4379525811"],"abstract_inverted_index":{"Corpus-based":[0],"set":[1,53,69,78],"expansion":[2,54,70,79,84],"refers":[3],"to":[4,20,29],"mining":[5],"\"sibling\"":[6],"entities":[7,12,66],"of":[8,39,65,83],"some":[9],"given":[10],"seed":[11],"from":[13],"a":[14],"corpus.":[15],"Previous":[16],"works":[17],"are":[18],"limited":[19],"using":[21],"either":[22],"textual":[23],"context":[24],"matching":[25,28,34],"or":[26],"semantic":[27],"fulfill":[30],"this":[31],"task.":[32,71],"Neither":[33],"method":[35],"takes":[36],"full":[37],"advantage":[38],"the":[40,68],"rich":[41],"information":[42],"in":[43,81],"free":[44],"text.":[45],"We":[46],"present":[47],"CaSE,":[48],"an":[49],"efficient":[50],"unsupervised":[51],"corpus-based":[52],"framework":[55],"that":[56,74],"leverages":[57],"lexical":[58],"features":[59],"as":[60,62],"well":[61],"distributed":[63],"representations":[64],"for":[67],"Experiments":[72],"show":[73],"CaSE":[75],"outperforms":[76],"state-of-the-art":[77],"algorithms":[80],"terms":[82],"accuracy.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}