{"id":"https://openalex.org/W2138433202","doi":"https://doi.org/10.3115/1034678.1034699","title":"Supervised grammar induction using training data with limited constituent information","display_name":"Supervised grammar induction using training data with limited constituent information","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2138433202","doi":"https://doi.org/10.3115/1034678.1034699","mag":"2138433202"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034699","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034699","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034699","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/10.3115/1034678.1034699","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070135550","display_name":"Rebecca Hwa","orcid":"https://orcid.org/0000-0003-1158-7014"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rebecca Hwa","raw_affiliation_strings":["Harvard University, Cambridge, MA","Harvard University, Cambridge, Ma.#TAB#"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University, Cambridge, Ma.#TAB#","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070135550"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":3.118,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.92262327,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"79"},"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8478093147277832},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8276789784431458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7667498588562012},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.6818124055862427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6729639768600464},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.596293568611145},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5930107235908508},{"id":"https://openalex.org/keywords/grammar-induction","display_name":"Grammar induction","score":0.4830651879310608},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4699333608150482},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4563570022583008},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2761671543121338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478093147277832},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8276789784431458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7667498588562012},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.6818124055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6729639768600464},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.596293568611145},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5930107235908508},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.4830651879310608},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4699333608150482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4563570022583008},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2761671543121338},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3115/1034678.1034699","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034699","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034699","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:10.1.1.12.9377","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.9377","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/P99-1010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.2668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.2668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.umiacs.umd.edu/~hwa/acl99.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.342.6971","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.342.6971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/cs/9905001v1.pdf","raw_type":"text"},{"id":"pmh:oai:acl.sr.language-archives.org:P99-1010","is_oa":false,"landing_page_url":"http://www.aclweb.org/anthology/P99-1010","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":""},{"id":"pmh:oai:americanae.aecid.es:3657107","is_oa":false,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3657107","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:10.3115/1034678.1034699","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034699","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034699","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":[{"display_name":"Quality Education","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2138433202.pdf","grobid_xml":"https://content.openalex.org/works/W2138433202.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1632114991","https://openalex.org/W1796802210","https://openalex.org/W1969005071","https://openalex.org/W1978470410","https://openalex.org/W2011725768","https://openalex.org/W2047706513","https://openalex.org/W2077302143","https://openalex.org/W2120670034","https://openalex.org/W2161204834","https://openalex.org/W2439178139","https://openalex.org/W3088560083","https://openalex.org/W3146125738","https://openalex.org/W4245826738","https://openalex.org/W4309986830"],"related_works":["https://openalex.org/W123468065","https://openalex.org/W2118045671","https://openalex.org/W4237776144","https://openalex.org/W1517025915","https://openalex.org/W3144287057","https://openalex.org/W2170837769","https://openalex.org/W2026740477","https://openalex.org/W1487802415","https://openalex.org/W2174380942","https://openalex.org/W171748267"],"abstract_inverted_index":{"Corpus-based":[0],"grammar":[1],"induction":[2,33],"generally":[3],"relies":[4],"on":[5],"hand-parsed":[6],"training":[7,42,82],"data":[8,83],"to":[9,30,117,125],"learn":[10],"the":[11,14,17,32,41,47,53,57],"structure":[12],"of":[13,19,73],"language.":[15],"Unfortunately,":[16],"cost":[18],"building":[20],"large":[21],"annotated":[22],"corpora":[23],"is":[24],"prohibitively":[25],"expensive.":[26],"This":[27],"work":[28],"aims":[29],"improve":[31],"strategy":[34],"when":[35],"there":[36],"are":[37,52],"few":[38],"labels":[39],"in":[40,56],"data.":[43],"We":[44],"show":[45],"that":[46,97,112],"most":[48],"informative":[49],"linguistic":[50],"constituents":[51,129],"higher":[54],"nodes":[55],"parse":[58,98],"trees,":[59],"typically":[60],"denoting":[61],"complex":[62],"noun":[63,133],"phrases":[64],"and":[65],"sentential":[66],"clauses.":[67],"They":[68],"account":[69],"for":[70,113],"only":[71,85],"20%":[72],"all":[74],"constituents.":[75],"For":[76],"inducing":[77],"grammars":[78,96,103],"from":[79,105],"sparsely":[80],"labeled":[81,107],"(e.g.,":[84],"higher-level":[86,128],"constituent":[87],"labels),":[88],"we":[89],"propose":[90],"an":[91],"<i>adaptation</i>":[92],"strategy,":[93],"which":[94],"produces":[95],"almost":[99],"as":[100,102],"well":[101],"induced":[104],"fully":[106],"corpora.":[108],"Our":[109],"results":[110],"suggest":[111],"a":[114],"partial":[115],"parser":[116],"replace":[118],"human":[119],"annotators,":[120],"it":[121],"must":[122],"be":[123],"able":[124],"automatically":[126],"extract":[127],"rather":[130],"than":[131],"base":[132],"phrases.":[134]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}