{"id":"https://openalex.org/W2107497465","doi":"https://doi.org/10.1017/s1351324900002308","title":"Evaluating two methods for Treebank grammar compaction","display_name":"Evaluating two methods for Treebank grammar compaction","publication_year":1999,"publication_date":"1999-12-01","ids":{"openalex":"https://openalex.org/W2107497465","doi":"https://doi.org/10.1017/s1351324900002308","mag":"2107497465"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324900002308","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002308","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/64B771AD8D758848C8FE8B1FE6134B42/S1351324900002308a.pdf/div-class-title-evaluating-two-methods-for-treebank-grammar-compaction-div.pdf","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"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/64B771AD8D758848C8FE8B1FE6134B42/S1351324900002308a.pdf/div-class-title-evaluating-two-methods-for-treebank-grammar-compaction-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079080634","display_name":"A V Krotov","orcid":"https://orcid.org/0000-0002-8050-5126"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"ALEXANDER KROTOV","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057386453","display_name":"Mark Hepple","orcid":"https://orcid.org/0000-0003-1488-257X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"MARK HEPPLE","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","alexk@dcs.shef.ac.uk, hepple@dcs.shef.ac.uk, robertg@dcs.shef.ac.uk, yorick@dcs. "],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"alexk@dcs.shef.ac.uk, hepple@dcs.shef.ac.uk, robertg@dcs.shef.ac.uk, yorick@dcs. ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040587162","display_name":"Robert Gaizauskas","orcid":"https://orcid.org/0000-0002-3356-5126"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"ROBERT GAIZAUSKAS","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050719415","display_name":"Yorick Wilks","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"YORICK WILKS","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","alexk@dcs.shef.ac.uk, hepple@dcs.shef.ac.uk, robertg@dcs.shef.ac.uk, yorick@dcs. "],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK;","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"alexk@dcs.shef.ac.uk, hepple@dcs.shef.ac.uk, robertg@dcs.shef.ac.uk, yorick@dcs. ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079080634"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.5973,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9079645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":"4","first_page":"377","last_page":"394"},"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":0.9980999827384949,"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":0.9657999873161316,"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":0.9014540314674377},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.8366093039512634},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8069471120834351},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7259095907211304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6644444465637207},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.6456212997436523},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.608510434627533},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4764167070388794},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4726635217666626},{"id":"https://openalex.org/keywords/context-free-grammar","display_name":"Context-free grammar","score":0.46132463216781616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13087883591651917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9014540314674377},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8366093039512634},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8069471120834351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7259095907211304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6644444465637207},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.6456212997436523},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.608510434627533},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4764167070388794},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4726635217666626},{"id":"https://openalex.org/C97212296","wikidata":"https://www.wikidata.org/wiki/Q338047","display_name":"Context-free grammar","level":3,"score":0.46132463216781616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13087883591651917},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324900002308","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002308","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/64B771AD8D758848C8FE8B1FE6134B42/S1351324900002308a.pdf/div-class-title-evaluating-two-methods-for-treebank-grammar-compaction-div.pdf","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:eprints.whiterose.ac.uk:1631","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1017/s1351324900002308","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002308","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/64B771AD8D758848C8FE8B1FE6134B42/S1351324900002308a.pdf/div-class-title-evaluating-two-methods-for-treebank-grammar-compaction-div.pdf","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"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2107497465.pdf","grobid_xml":"https://content.openalex.org/works/W2107497465.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W66942725","https://openalex.org/W1507020546","https://openalex.org/W1551104980","https://openalex.org/W1567570606","https://openalex.org/W1632114991","https://openalex.org/W1973717701","https://openalex.org/W1977707485","https://openalex.org/W2011725768","https://openalex.org/W2110882317","https://openalex.org/W2116915753","https://openalex.org/W2118785474","https://openalex.org/W2153439141","https://openalex.org/W2161204834","https://openalex.org/W2162539697","https://openalex.org/W2726537443","https://openalex.org/W2741544463","https://openalex.org/W2891979318"],"related_works":["https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W2109902858","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2017946383","https://openalex.org/W2104399512"],"abstract_inverted_index":{"Treebanks,":[0],"such":[1],"as":[2],"the":[3,10,18,27,30,50,57,79],"Penn":[4],"Treebank,":[5],"provide":[6],"a":[7,34,67,97,114,121,143],"basis":[8],"for":[9,49],"automatic":[11],"creation":[12],"of":[13,29,54,81,84,88,93,99,117],"broad":[14],"coverage":[15],"grammars.":[16],"In":[17,59],"simplest":[19],"case,":[20],"rules":[21,89],"can":[22,43,70,125],"simply":[23],"be":[24,44,71,126],"\u2018read":[25],"off\u2019":[26],"parse-annotations":[28],"corpus,":[31],"producing":[32],"either":[33],"simple":[35],"or":[36,75],"probabilistic":[37,105,122],"context-free":[38,123],"grammar.":[39,58],"Such":[40],"grammars,":[41],"however,":[42],"very":[45],"large,":[46],"presenting":[47],"problems":[48],"subsequent":[51],"computational":[52],"costs":[53],"parsing":[55,136],"under":[56],"this":[60],"paper,":[61],"we":[62],"explore":[63],"ways":[64],"by":[65,90,113,130,139],"which":[66,77,102],"treebank":[68],"grammar":[69,124],"reduced":[72,127],"in":[73,128,135,145,150],"size":[74,129],"\u2018compacted\u2019,":[76],"involve":[78],"use":[80,116],"two":[82,119],"kinds":[83],"technique:":[85],"(i)":[86],"thresholding":[87],"their":[91],"number":[92],"occurrences;":[94],"and":[95,106,138],"(ii)":[96],"method":[98],"rule-parsing":[100],",":[101],"has":[103],"both":[104],"non-probabilistic":[107],"variants.":[108],"Our":[109],"results":[110],"show":[111],"that":[112],"combined":[115],"these":[118],"techniques,":[120],"62%":[131],"without":[132],"any":[133],"loss":[134,149],"performance,":[137],"71%":[140],"to":[141],"give":[142],"gain":[144],"recall,":[146],"but":[147],"some":[148],"precision.":[151]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
