{"id":"https://openalex.org/W1660018656","doi":"https://doi.org/10.48550/arxiv.cmp-lg/9406039","title":"Three studies of grammar-based surface-syntactic parsing of unrestricted English text. A summary and orientation","display_name":"Three studies of grammar-based surface-syntactic parsing of unrestricted English text. A summary and orientation","publication_year":1994,"publication_date":"1994-06-27","ids":{"openalex":"https://openalex.org/W1660018656","doi":"https://doi.org/10.48550/arxiv.cmp-lg/9406039","mag":"1660018656"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:cmp-lg/9406039","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cmp-lg/9406039","pdf_url":"https://arxiv.org/pdf/cmp-lg/9406039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/cmp-lg/9406039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111477267","display_name":"Atro Voutilainen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Voutilainen, Atro","raw_affiliation_strings":["Research Unit for Computational Linguistics, University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Unit for Computational Linguistics, University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111477267"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/constraint-grammar","display_name":"constraint grammar","score":0.7509999871253967},{"id":"https://openalex.org/keywords/morphological-disambiguation","display_name":"morphological disambiguation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/part-of-speech-disambiguation","display_name":"part-of-speech disambiguation","score":0.949999988079071},{"id":"https://openalex.org/keywords/english-text","display_name":"English text","score":0.3089999854564667},{"id":"https://openalex.org/keywords/lexical-ambiguity-resolution","display_name":"lexical ambiguity resolution","score":0.31700000166893005}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7597267627716064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6878403425216675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494722366333008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702338814735413},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5679946541786194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5581833124160767},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.5113579630851746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16695058345794678},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12433412671089172},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.05585962533950806}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:cmp-lg/9406039","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cmp-lg/9406039","pdf_url":"https://arxiv.org/pdf/cmp-lg/9406039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cds.cern.ch:495193","doi":null,"is_oa":false,"landing_page_url":"http://cds.cern.ch/record/495193","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.cmp-lg/9406039","doi":"https://doi.org/10.48550/arxiv.cmp-lg/9406039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.cmp-lg/9406039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:cmp-lg/9406039","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/cmp-lg/9406039","pdf_url":"https://arxiv.org/pdf/cmp-lg/9406039","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W2358855848","https://openalex.org/W6643695","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830"],"abstract_inverted_index":{"The":[0,47,67,86],"dissertation":[1],"addresses":[2,151],"the":[3,39,54,60,80,90,114,121,124,135,140,152,162,182,187],"design":[4],"of":[5,12,18,35,53,83,89,100,113,123,142,154,186],"parsing":[6],"grammars":[7],"for":[8,30,179],"automatic":[9],"surface-syntactic":[10],"analysis":[11],"unconstrained":[13],"English":[14],"text.":[15],"It":[16],"consists":[17],"a":[19,28],"summary":[20],"and":[21,169,176,189],"three":[22],"articles.":[23],"{\\it":[24,147],"Morphological":[25],"disambiguation}":[26],"documents":[27],"grammar":[29],"morphological":[31,56,84,91,163],"(or":[32],"part-of-speech)":[33],"disambiguation":[34,174],"English,":[36],"done":[37],"within":[38],"Constraint":[40],"Grammar":[41],"framework":[42],"proposed":[43,58],"by":[44,59],"Fred":[45],"Karlsson.":[46],"disambiguator":[48,92],"seeks":[49],"to":[50,110,127,134,156,194],"discard":[51],"those":[52,158],"alternative":[55],"analyses":[57],"lexical":[61],"analyser":[62],"that":[63,99,106,160],"are":[64,108,167],"contextually":[65],"illegitimate.":[66],"1,100":[68],"constraints":[69,175],"express":[70],"some":[71,112],"23":[72],"general,":[73],"essentially":[74],"syntactic":[75],"statements":[76],"as":[77],"restrictions":[78],"on":[79],"linear":[81],"order":[82],"tags.":[85],"error":[87],"rate":[88],"is":[93],"about":[94],"ten":[95],"times":[96],"smaller":[97],"than":[98],"another":[101],"state-of-the-art":[102],"probabilistic":[103,143],"disambiguator,":[104],"given":[105],"both":[107],"allowed":[109],"leave":[111],"hardest":[115],"ambiguities":[116,159],"unresolved.":[117],"This":[118],"accuracy":[119],"suggests":[120],"viability":[122,141],"grammar-based":[125],"approach":[126],"natural":[128],"language":[129],"parsing,":[130],"thus":[131],"also":[132],"contributing":[133],"more":[136],"general":[137],"debate":[138],"concerning":[139],"vs.\\":[144],"linguistic":[145],"techniques.":[146],"Experiments":[148],"with":[149],"heuristics}":[150],"question":[153],"how":[155],"resolve":[157],"survive":[161],"disambiguator.":[164],"Two":[165],"approaches":[166],"presented":[168],"empirically":[170],"evaluated:":[171],"(i)":[172],"heuristic":[173],"(ii)":[177],"techniques":[178],"learning":[180],"from":[181],"fully":[183],"disambiguated":[184],"part":[185],"corpus":[188],"then":[190],"applying":[191],"this":[192],"information":[193],"resolving":[195],"remaining":[196],"ambiguities.":[197]},"counts_by_year":[],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}
