{"id":"https://openalex.org/W2009000964","doi":"https://doi.org/10.1145/2407736.2407737","title":"An information-theoretic measure to evaluate parsing difficulty across treebanks","display_name":"An information-theoretic measure to evaluate parsing difficulty across treebanks","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2009000964","doi":"https://doi.org/10.1145/2407736.2407737","mag":"2009000964"},"language":"en","primary_location":{"id":"doi:10.1145/2407736.2407737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407736.2407737","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064332237","display_name":"Anna Corazza","orcid":"https://orcid.org/0000-0002-9156-5079"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Anna Corazza","raw_affiliation_strings":["Universit\u00e0 di Napoli \u201cFederico II\u201d, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Napoli \u201cFederico II\u201d, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073069826","display_name":"Alberto Lavelli","orcid":"https://orcid.org/0000-0002-7175-6804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Lavelli","raw_affiliation_strings":["FBK-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"FBK-irst, Trento, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068504877","display_name":"Giorgio Satta","orcid":"https://orcid.org/0000-0001-7742-6438"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Satta","raw_affiliation_strings":["Universit\u00e0 di Padova, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064332237"],"corresponding_institution_ids":["https://openalex.org/I71267560"],"apc_list":null,"apc_paid":null,"fwci":0.4809,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7500216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"9","issue":"4","first_page":"1","last_page":"31"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9959999918937683,"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/parsing","display_name":"Parsing","score":0.8830684423446655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078850507736206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.635303258895874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6273398399353027},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6118603944778442},{"id":"https://openalex.org/keywords/top-down-parsing","display_name":"Top-down parsing","score":0.526328980922699},{"id":"https://openalex.org/keywords/bottom-up-parsing","display_name":"Bottom-up parsing","score":0.4969811737537384},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.494615763425827},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.42487356066703796},{"id":"https://openalex.org/keywords/s-attributed-grammar","display_name":"S-attributed grammar","score":0.42462027072906494},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1448715627193451},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11791461706161499}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8830684423446655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078850507736206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635303258895874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6273398399353027},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6118603944778442},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.526328980922699},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.4969811737537384},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.494615763425827},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.42487356066703796},{"id":"https://openalex.org/C147547768","wikidata":"https://www.wikidata.org/wiki/Q3113342","display_name":"S-attributed grammar","level":3,"score":0.42462027072906494},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1448715627193451},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11791461706161499},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2407736.2407737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407736.2407737","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:www.research.unipd.it:11577/2572711","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/2572711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2697047302","display_name":null,"funder_award_id":"IST-FP6-026978","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W108437174","https://openalex.org/W199541590","https://openalex.org/W200279514","https://openalex.org/W1498112152","https://openalex.org/W1508165687","https://openalex.org/W1535015163","https://openalex.org/W1549364818","https://openalex.org/W1551104980","https://openalex.org/W1574901103","https://openalex.org/W1579838312","https://openalex.org/W1632114991","https://openalex.org/W1865928303","https://openalex.org/W1965364888","https://openalex.org/W1982944197","https://openalex.org/W1985754308","https://openalex.org/W1994851566","https://openalex.org/W2000566875","https://openalex.org/W2010588484","https://openalex.org/W2022096665","https://openalex.org/W2052449326","https://openalex.org/W2073791458","https://openalex.org/W2079145130","https://openalex.org/W2087165009","https://openalex.org/W2087435614","https://openalex.org/W2092654472","https://openalex.org/W2093474734","https://openalex.org/W2096175520","https://openalex.org/W2097606805","https://openalex.org/W2098050104","https://openalex.org/W2098379588","https://openalex.org/W2098949613","https://openalex.org/W2099111195","https://openalex.org/W2099896133","https://openalex.org/W2100448020","https://openalex.org/W2104029044","https://openalex.org/W2106578604","https://openalex.org/W2129056111","https://openalex.org/W2135057643","https://openalex.org/W2138389163","https://openalex.org/W2139621418","https://openalex.org/W2149741699","https://openalex.org/W2155693943","https://openalex.org/W2160842254","https://openalex.org/W2161204834","https://openalex.org/W2166306133","https://openalex.org/W2167072947","https://openalex.org/W2170469979","https://openalex.org/W2183656857","https://openalex.org/W2216065124","https://openalex.org/W2333790164","https://openalex.org/W2343954916","https://openalex.org/W2736671181","https://openalex.org/W2930957955","https://openalex.org/W3004035325","https://openalex.org/W3198456432"],"related_works":["https://openalex.org/W3088470625","https://openalex.org/W3143982968","https://openalex.org/W2792937288","https://openalex.org/W3035970863","https://openalex.org/W2619584063","https://openalex.org/W4320024782","https://openalex.org/W2389755172","https://openalex.org/W2952780262","https://openalex.org/W2804916787","https://openalex.org/W1975821179"],"abstract_inverted_index":{"With":[0],"the":[1,14,48,51,70,95,98],"growing":[2],"interest":[3],"in":[4,61,126,133],"statistical":[5],"parsing,":[6],"special":[7],"attention":[8],"has":[9],"recently":[10],"been":[11],"devoted":[12],"to":[13,20,29,32,80],"problem":[15],"of":[16,50,94,97,120],"comparing":[17,40],"different":[18],"treebanks":[19,44,105],"assess":[21],"which":[22],"languages":[23],"or":[24],"domains":[25],"are":[26],"more":[27],"difficult":[28],"parse":[30],"relative":[31],"a":[33,92,131],"given":[34],"model.":[35,99],"A":[36],"common":[37],"methodology":[38],"for":[39,106],"parsing":[41,121,134],"difficulty":[42],"across":[43,103],"is":[45,84,116],"based":[46],"on":[47],"use":[49],"standard":[52,81],"labeled":[53],"precision":[54],"and":[55,110,112],"recall":[56],"measures.":[57],"As":[58],"an":[59,66,117,124],"alternative,":[60],"this":[62],"article":[63],"we":[64],"propose":[65],"information-theoretic":[67],"measure,":[68],"called":[69],"expected":[71],"conditional":[72],"cross-entropy":[73],"(ECC).":[74],"One":[75],"important":[76],"advantage":[77],"with":[78,123],"respect":[79],"performance":[82],"measures":[83],"that":[85,114],"ECC":[86,102,115,127],"can":[87],"be":[88],"directly":[89],"expressed":[90],"as":[91],"function":[93],"parameters":[96],"We":[100],"evaluate":[101],"several":[104],"English,":[107],"French,":[108],"German,":[109],"Italian,":[111],"show":[113],"effective":[118],"measure":[119],"difficulty,":[122],"increase":[125],"always":[128],"accompanied":[129],"by":[130],"degradation":[132],"accuracy.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}