{"id":"https://openalex.org/W28706907","doi":null,"title":"Data-oriented parsing and the Penn Chinese treebank","display_name":"Data-oriented parsing and the Penn Chinese treebank","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W28706907","mag":"28706907"},"language":"en","primary_location":{"id":"pmh:http://www.rian.ie/44698/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15823/","pdf_url":"http://doras.dcu.ie/15823/","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hearne, Mary and Way, Andy ORCID: 0000-0001-5736-5930 &lt;https://orcid.org/0000-0001-5736-5930&gt; (2004) Data-oriented parsing and the Penn Chinese treebank. In: IJCNLP 2004 - 1st International Joint Conference on Natural Language Processing, 22-24 March 2004, Hainan Island, China.","raw_type":"Other"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doras.dcu.ie/15823/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038985518","display_name":"Mary Hearne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mary Hearne","raw_affiliation_strings":["Dublin City University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dublin City University#TAB#","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055864641","display_name":"Andy Way","orcid":"https://orcid.org/0000-0001-5736-5930","observed_orcids":["https://orcid.org/0000-0001-5736-5930"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Way","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5736-5930","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9497,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70559153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-oriented-parsing","display_name":"data-oriented parsing","score":0.9860000014305115},{"id":"https://openalex.org/keywords/penn-chinese-treebank","display_name":"Penn Chinese Treebank","score":0.9160000085830688},{"id":"https://openalex.org/keywords/chinese-parsing","display_name":"Chinese parsing","score":0.6940000057220459},{"id":"https://openalex.org/keywords/parsing-efficiency","display_name":"parsing efficiency","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9754793643951416},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.9054478406906128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847391366958618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7597443461418152},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.7006469964981079},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.6896796226501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463353037834167},{"id":"https://openalex.org/C118364021","wikidata":"https://www.wikidata.org/wiki/Q7139956","display_name":"Parser combinator","level":3,"score":0.5263028144836426},{"id":"https://openalex.org/C166651950","wikidata":"https://www.wikidata.org/wiki/Q7824365","display_name":"Top-down parsing language","level":5,"score":0.523749828338623},{"id":"https://openalex.org/C147547768","wikidata":"https://www.wikidata.org/wiki/Q3113342","display_name":"S-attributed grammar","level":3,"score":0.521660327911377},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.509318470954895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4194391667842865},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:http://www.rian.ie/44698/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15823/","pdf_url":"http://doras.dcu.ie/15823/","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hearne, Mary and Way, Andy ORCID: 0000-0001-5736-5930 &lt;https://orcid.org/0000-0001-5736-5930&gt; (2004) Data-oriented parsing and the Penn Chinese treebank. In: IJCNLP 2004 - 1st International Joint Conference on Natural Language Processing, 22-24 March 2004, Hainan Island, China.","raw_type":"Other"},{"id":"pmh:oai:doras.dcu.ie:15823","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0001-5736-5930>","pdf_url":"https://doras.dcu.ie/15823/1/Data-Oriented_Parsing_and_the_Penn_Chinese_Treebank.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"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":"Conference or Workshop Item"},{"id":"mag:28706907","doi":null,"is_oa":false,"landing_page_url":"http://computing.dcu.ie/~away/PUBS/2004/ijcnlp-04-camera.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:http://www.rian.ie/44698/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15823/","pdf_url":"http://doras.dcu.ie/15823/","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hearne, Mary and Way, Andy ORCID: 0000-0001-5736-5930 &lt;https://orcid.org/0000-0001-5736-5930&gt; (2004) Data-oriented parsing and the Penn Chinese treebank. In: IJCNLP 2004 - 1st International Joint Conference on Natural Language Processing, 22-24 March 2004, Hainan Island, China.","raw_type":"Other"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W28706907.pdf","grobid_xml":"https://content.openalex.org/works/W28706907.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W171594975","https://openalex.org/W185466456","https://openalex.org/W1498668018","https://openalex.org/W1539587067","https://openalex.org/W1557279510","https://openalex.org/W1564942370","https://openalex.org/W1571339177","https://openalex.org/W1669992767","https://openalex.org/W1822852248","https://openalex.org/W2000566875","https://openalex.org/W2020477116","https://openalex.org/W2079326125","https://openalex.org/W2096204319","https://openalex.org/W2110651511","https://openalex.org/W2146113428","https://openalex.org/W2152302696","https://openalex.org/W2162539697","https://openalex.org/W2167072947","https://openalex.org/W2343945585","https://openalex.org/W2394484132","https://openalex.org/W2403315715","https://openalex.org/W2430687117"],"related_works":["https://openalex.org/W1499470996","https://openalex.org/W1533853787","https://openalex.org/W7098587466","https://openalex.org/W2113466837","https://openalex.org/W7097050081","https://openalex.org/W6986525527","https://openalex.org/W2250386557","https://openalex.org/W7096045332","https://openalex.org/W1844099549","https://openalex.org/W2101978633"],"abstract_inverted_index":{"We":[0,47],"present":[1],"an":[2,17],"investigation":[3],"into":[4,55],"parsing":[5,53,84,161],"the":[6,28,39,85,155,162],"Penn":[7,86,163],"Chinese":[8,87,164],"Treebank":[9],"using":[10],"a":[11,56,62,92,125],"Data-Oriented":[12],"Parsing":[13],"(DOP)":[14],"approach.":[15],"DOP\\ncomprises":[16],"experience-based":[18],"approach":[19,41,115],"to":[20,80],"natural":[21],"language":[22],"parsing.":[23],"Most":[24],"published":[25,110],"research":[26],"in":[27,51,100,111,139],"DOP":[29,40,52,58,149],"framework":[30],"uses":[31],"PStrees":[32],"as":[33],"its":[34],"representation":[35,64],"schema.":[36],"Drawbacks":[37],"of":[38,45,65,102,120],"centre":[42],"around":[43],"issues":[44],"efficiency.":[46],"incorporate":[48],"recent":[49],"advances":[50],"techniques":[54],"novel":[57],"parser":[59],"which":[60,68,136],"generates":[61],"compact":[63],"all":[66],"subtrees":[67],"can":[69,143],"be":[70,144],"derived":[71],"from":[72],"any":[73],"full":[74],"parse":[75],"tree.\\nWe":[76],"compare":[77],"our":[78,98,114,148],"work":[79,82,142],"previous":[81,141],"on":[83],"Treebank,":[88],"and":[89,94,104],"provide":[90],"both":[91],"quantitative":[93],"qualitative":[95],"evaluation.":[96],"While":[97],"results":[99],"terms":[101],"Precision":[103],"Recall":[105],"are":[106],"slightly":[107],"below":[108],"those":[109],"related":[112],"research,":[113],"requires":[116],"no":[117],"manual":[118],"encoding":[119],"head":[121],"rules,":[122],"nor":[123],"is":[124,158],"development":[126],"phase":[127],"per":[128],"se":[129],"necessary.\\nWe":[130],"also":[131],"note":[132],"that":[133,154],"certain":[134],"constructions":[135],"were":[137],"problematic":[138],"this":[140],"handled":[145],"correctly":[146],"by":[147],"parser.":[150],"Finally,":[151],"we":[152],"observe":[153],"\u2018DOP":[156],"Hypothesis\u2019":[157],"confirmed":[159],"for":[160],"Treebank.":[165]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
