{"id":"https://openalex.org/W2069403915","doi":"https://doi.org/10.1017/s1351324906004128","title":"From UBGs to CFGs A practical corpus-driven approach","display_name":"From UBGs to CFGs A practical corpus-driven approach","publication_year":2006,"publication_date":"2006-04-26","ids":{"openalex":"https://openalex.org/W2069403915","doi":"https://doi.org/10.1017/s1351324906004128","mag":"2069403915"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324906004128","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004128","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://dx.doi.org/10.22028/D291-25210","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109393950","display_name":"Hans\u2010Ulrich Krieger","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"HANS-ULRICH KRIEGER","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Stuhlsatzenhausweg 3, D-66123 Saarbriicken, Germany e-mail:","German research center for artificial intelligence (dfki), stuhlsatzenhausweg 3, d-66123 saarbriicken, germany e-mail: krieger@dfki.de#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Stuhlsatzenhausweg 3, D-66123 Saarbriicken, Germany e-mail:","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German research center for artificial intelligence (dfki), stuhlsatzenhausweg 3, d-66123 saarbriicken, germany e-mail: krieger@dfki.de#TAB#","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109393950"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.10964254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"13","issue":"4","first_page":"317","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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":0.9991999864578247,"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":0.9097417593002319},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.7516312599182129},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7278637886047363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6812365651130676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6801062226295471},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5363214612007141},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.5254579782485962},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4691929519176483},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4294233024120331},{"id":"https://openalex.org/keywords/context-free-grammar","display_name":"Context-free grammar","score":0.41412627696990967},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3962246775627136},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18605363368988037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9097417593002319},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.7516312599182129},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7278637886047363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6812365651130676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801062226295471},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5363214612007141},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.5254579782485962},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4691929519176483},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4294233024120331},{"id":"https://openalex.org/C97212296","wikidata":"https://www.wikidata.org/wiki/Q338047","display_name":"Context-free grammar","level":3,"score":0.41412627696990967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3962246775627136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18605363368988037},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1017/s1351324906004128","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324906004128","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:publikationen.sulb.uni-saarland.de:20.500.11880/25266","is_oa":true,"landing_page_url":"http://dx.doi.org/10.22028/D291-25210","pdf_url":null,"source":{"id":"https://openalex.org/S4377196383","display_name":"Publications of the UdS (Saarland University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I91712215","host_organization_name":"Saarland University","host_organization_lineage":["https://openalex.org/I91712215"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:report"},{"id":"doi:10.22028/d291-25210","is_oa":true,"landing_page_url":"https://doi.org/10.22028/d291-25210","pdf_url":null,"source":{"id":"https://openalex.org/S7407052975","display_name":"Universit\u00e4t des Saarlandes","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"report"}],"best_oa_location":{"id":"pmh:oai:publikationen.sulb.uni-saarland.de:20.500.11880/25266","is_oa":true,"landing_page_url":"http://dx.doi.org/10.22028/D291-25210","pdf_url":null,"source":{"id":"https://openalex.org/S4377196383","display_name":"Publications of the UdS (Saarland University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I91712215","host_organization_name":"Saarland University","host_organization_lineage":["https://openalex.org/I91712215"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:report"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W203959070","https://openalex.org/W398856391","https://openalex.org/W615227492","https://openalex.org/W1491178396","https://openalex.org/W1499266548","https://openalex.org/W1503851918","https://openalex.org/W1538023239","https://openalex.org/W1539395461","https://openalex.org/W1544084920","https://openalex.org/W1585955963","https://openalex.org/W1589712742","https://openalex.org/W1753112791","https://openalex.org/W1769373918","https://openalex.org/W1938853666","https://openalex.org/W1972573551","https://openalex.org/W1973163809","https://openalex.org/W1978470410","https://openalex.org/W1988519408","https://openalex.org/W1994851566","https://openalex.org/W1997289673","https://openalex.org/W1997409097","https://openalex.org/W2002089154","https://openalex.org/W2003768046","https://openalex.org/W2008236074","https://openalex.org/W2011623898","https://openalex.org/W2017668684","https://openalex.org/W2032527312","https://openalex.org/W2038248725","https://openalex.org/W2063747743","https://openalex.org/W2079834019","https://openalex.org/W2082818164","https://openalex.org/W2086832429","https://openalex.org/W2097730343","https://openalex.org/W2105899789","https://openalex.org/W2112115709","https://openalex.org/W2114057609","https://openalex.org/W2123550348","https://openalex.org/W2130747650","https://openalex.org/W2139974778","https://openalex.org/W2143144395","https://openalex.org/W2143745167","https://openalex.org/W2145375832","https://openalex.org/W2147869709","https://openalex.org/W2170336504","https://openalex.org/W2439178139","https://openalex.org/W2483327705","https://openalex.org/W2737659430","https://openalex.org/W2912188639","https://openalex.org/W2949918103","https://openalex.org/W3021430701","https://openalex.org/W3037539091","https://openalex.org/W4206462942","https://openalex.org/W4231862177","https://openalex.org/W4245826738","https://openalex.org/W4285719527","https://openalex.org/W4302339081"],"related_works":["https://openalex.org/W2085190866","https://openalex.org/W131152816","https://openalex.org/W3107474891","https://openalex.org/W3037160427","https://openalex.org/W3013856176","https://openalex.org/W2112488502","https://openalex.org/W1507396723","https://openalex.org/W4230394326","https://openalex.org/W2057155004","https://openalex.org/W1588450363"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"present":[2],"a":[3,51,56,76,96,143,157,162,176,184],"simple":[4],"and":[5,49,189],"intuitive":[6],"unsound":[7,150],"corpus-driven":[8,177],"approximation":[9,147],"method":[10,148,178],"for":[11,42,91,111,120],"turning":[12],"unification-based":[13,113,172],"grammars,":[14],"such":[15,123],"as":[16,124],"HPSG,":[17],"CLE,":[18],"or":[19,127],"PATR-II":[20],"into":[21,222],"context-free":[22,134,224],"grammars":[23,39],"(CFGs).":[24],"Our":[25,198],"research":[26],"is":[27,149,161,175],"motivated":[28],"by":[29,74,169,218],"the":[30,43,92,101,112,139,166,170,214,223],"idea":[31],"that":[32,152,180],"we":[33],"can":[34,201],"exploit":[35],"(large-scale),":[36],"hand-written":[37],"unification":[38,93],"not":[40,155],"only":[41],"purpose":[44],"of":[45,142,165,186],"describing":[46],"natural":[47],"language":[48,135,160,167],"obtaining":[50],"syntactic":[52],"structure":[53],"(and":[54],"perhaps":[55],"semantic":[57],"form),":[58],"but":[59],"also":[60],"to":[61,69,84,116,132,209,213],"address":[62],"several":[63],"other":[64],"very":[65],"practical":[66],"topics.":[67],"Firstly,":[68],"speed":[70],"up":[71],"deep":[72],"parsing":[73,89],"having":[75],"cheap":[77],"recognition":[78],"pre-flter":[79],"(the":[80],"approximated":[81,102],"CFG).":[82],"Secondly,":[83],"obtain":[85],"an":[86,107],"indirect":[87],"stochastic":[88],"model":[90,110,141],"grammar":[94],"through":[95],"trained":[97],"PCFG,":[98],"obtained":[99],"from":[100],"CFG.":[103],"This":[104],"gives":[105],"us":[106,208],"efficient":[108],"disambiguation":[109],"grammar.":[114,173],"Thirdly,":[115],"generate":[117,156],"domain-specific":[118],"subgrammars":[119],"application":[121],"areas":[122],"information":[125,221],"extraction":[126],"question":[128],"answering.":[129],"And":[130],"finally,":[131],"compile":[133],"models":[136],"which":[137],"assist":[138],"acoustic":[140],"speech":[144],"recognizer.":[145],"The":[146,226],"in":[151,179,204,232],"it":[153,181],"does":[154],"CFG":[158],"whose":[159],"true":[163],"superset":[164],"accepted":[168],"original":[171,215],"It":[174],"relies":[182],"on":[183],"corpus":[185],"parsed":[187],"sentences":[188],"generates":[190],"broader":[191],"CFGs":[192],"when":[193],"given":[194],"more":[195,220],"input":[196],"samples.":[197],"open":[199],"approach":[200,227],"be":[202],"fine-tuned":[203],"different":[205],"directions,":[206],"allowing":[207],"monotonically":[210],"come":[211],"close":[212],"parse":[216],"trees":[217],"shifting":[219],"symbols.":[225],"has":[228],"been":[229],"fully":[230],"implemented":[231],"JAVA":[233],".":[234]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
