{"id":"https://openalex.org/W2251405440","doi":"https://doi.org/10.3115/v1/w14-1611","title":"Improved Pattern Learning for Bootstrapped Entity Extraction","display_name":"Improved Pattern Learning for Bootstrapped Entity Extraction","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251405440","doi":"https://doi.org/10.3115/v1/w14-1611","mag":"2251405440"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-1611","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1611","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w14-1611","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045050802","display_name":"Sonal Gupta","orcid":"https://orcid.org/0000-0002-2096-4662"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sonal Gupta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Manning","raw_affiliation_strings":["Stanford University ()"],"affiliations":[{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045050802"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.5313,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.98844294,"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":"98","last_page":"108"},"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019096255302429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6718886494636536},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6057268381118774},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47663912177085876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4542555809020996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4438042938709259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3394421935081482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10960027575492859},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06841158866882324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019096255302429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6718886494636536},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6057268381118774},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47663912177085876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4542555809020996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4438042938709259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3394421935081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10960027575492859},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06841158866882324},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-1611","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1611","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.498.4613","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.498.4613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-nlp.stanford.edu/pubs/gupta14evalpatterns.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.695","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-1611.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-1611","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1611","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.5799999833106995,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W69597389","https://openalex.org/W1499578805","https://openalex.org/W1554734378","https://openalex.org/W1565759278","https://openalex.org/W1565862766","https://openalex.org/W1971563386","https://openalex.org/W1996430422","https://openalex.org/W2038721957","https://openalex.org/W2068737686","https://openalex.org/W2097101873","https://openalex.org/W2102448616","https://openalex.org/W2104411075","https://openalex.org/W2107391405","https://openalex.org/W2110914363","https://openalex.org/W2112646584","https://openalex.org/W2121227244","https://openalex.org/W2121855012","https://openalex.org/W2124634352","https://openalex.org/W2128955272","https://openalex.org/W2129842875","https://openalex.org/W2132655161","https://openalex.org/W2133108446","https://openalex.org/W2134368421","https://openalex.org/W2143349571","https://openalex.org/W2148540243","https://openalex.org/W2152430007","https://openalex.org/W2158049734","https://openalex.org/W2167187514","https://openalex.org/W2201604718","https://openalex.org/W2250265269","https://openalex.org/W2785349534"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2961085424","https://openalex.org/W2350529538","https://openalex.org/W2327130486"],"abstract_inverted_index":{"Bootstrapped":[0],"pattern":[1,68,103],"learning":[2],"for":[3,106],"entity":[4],"extraction":[5],"usually":[6],"starts":[7],"with":[8],"seed":[9],"entities":[10,16,47,109],"and":[11,15,31,86,89,93],"iteratively":[12],"learns":[13],"patterns":[14],"from":[17,110],"unlabeled":[18,46,75],"text.":[19],"Patterns":[20],"are":[21,48,55],"scored":[22],"by":[23,57,70],"their":[24],"ability":[25],"to":[26,40,51,96],"extract":[27],"more":[28],"positive":[29],"en-tities":[30],"less":[32],"negative":[33,53],"entities.":[34,76,98],"A":[35],"prob-lem":[36],"is":[37],"that":[38],"due":[39],"the":[41,58,72],"lack":[42],"of":[43,74],"labeled":[44],"data,":[45],"either":[49],"assumed":[50],"be":[52],"or":[54],"ignored":[56],"existing":[59,102],"pat-tern":[60],"scoring":[61,69],"measures.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"improve":[67],"predicting":[71],"labels":[73],"We":[77],"use":[78],"var-ious":[79],"unsupervised":[80],"features":[81],"based":[82],"on":[83],"con-trasting":[84],"domain-specific":[85],"general":[87],"text,":[88],"exploiting":[90],"distributional":[91],"similarity":[92],"edit":[94],"distances":[95],"learned":[97],"Our":[99],"system":[100],"outperforms":[101],"scor-ing":[104],"algorithms":[105],"extracting":[107],"drug-and-treatment":[108],"four":[111],"medical":[112],"fo-rums.":[113],"1":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}