{"id":"https://openalex.org/W2160587453","doi":"https://doi.org/10.3115/1034678.1034697","title":"Finding parts in very large corpora","display_name":"Finding parts in very large corpora","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2160587453","doi":"https://doi.org/10.3115/1034678.1034697","mag":"2160587453"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034697","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034697","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034697","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","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/10.3115/1034678.1034697","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077534970","display_name":"Matthew Berland","orcid":"https://orcid.org/0000-0002-5457-1461"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Berland","raw_affiliation_strings":["Brown University, Providence, RI"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005380528","display_name":"Eugene Charniak","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Charniak","raw_affiliation_strings":["Brown University, Providence, RI"],"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077534970"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":7.2762,"has_fulltext":true,"cited_by_count":467,"citation_normalized_percentile":{"value":0.97099765,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/wordnet","display_name":"WordNet","score":0.9331026077270508},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8322720527648926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047759532928467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7177067995071411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6711663007736206},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5899630188941956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5529784560203552}],"concepts":[{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.9331026077270508},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8322720527648926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047759532928467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7177067995071411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6711663007736206},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5899630188941956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5529784560203552},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1034678.1034697","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034697","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034697","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.4257","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.4257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P99/P99-1008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.559","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/people/ec/papers/fp99.ps","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:P99-1008","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/P99-1008","pdf_url":null,"source":{"id":"https://openalex.org/S4306402137","display_name":"The COCOON platform (University of Paris)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/1034678.1034697","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034697","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034697","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2811237814","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3253741400","display_name":"Improved Statistical Language Models","funder_award_id":"9319516","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"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160587453.pdf","grobid_xml":"https://content.openalex.org/works/W2160587453.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1930023685","https://openalex.org/W1977182536","https://openalex.org/W2068737686","https://openalex.org/W2102381086","https://openalex.org/W2109190044","https://openalex.org/W2116780029","https://openalex.org/W2161669948","https://openalex.org/W2166776180","https://openalex.org/W2199803028","https://openalex.org/W2787893582","https://openalex.org/W2952509172","https://openalex.org/W2964023183","https://openalex.org/W4255198209"],"related_works":["https://openalex.org/W1499795620","https://openalex.org/W112738600","https://openalex.org/W252296781","https://openalex.org/W2135707795","https://openalex.org/W1537146566","https://openalex.org/W2331034580","https://openalex.org/W1517978361","https://openalex.org/W4376623067","https://openalex.org/W3002840018","https://openalex.org/W2040535673"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,16,59,62],"method":[3,21],"for":[4,28],"extracting":[5],"parts":[6],"of":[7,61],"objects":[8],"from":[9,13],"wholes":[10],"(e.g.":[11],"\"speedometer\"":[12],"\"car\").":[14],"Given":[15],"very":[17],"large":[18],"corpus":[19],"our":[20],"finds":[22],"part":[23,39,60],"words":[24,32],"with":[25],"55%":[26],"accuracy":[27],"the":[29,36],"top":[30],"50":[31],"as":[33,54,58],"ranked":[34],"by":[35,44],"system.":[37],"The":[38],"list":[40],"could":[41],"be":[42],"scanned":[43],"an":[45,50],"end-user":[46],"and":[47],"added":[48],"to":[49],"existing":[51],"ontology":[52],"(such":[53],"WordNet),":[55],"or":[56],"used":[57],"rough":[63],"semantic":[64],"lexicon.":[65]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":34}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
