{"id":"https://openalex.org/W2250496306","doi":"https://doi.org/10.3115/v1/w14-1820","title":"Assessing the Readability of Sentences: Which Corpora and Features?","display_name":"Assessing the Readability of Sentences: Which Corpora and Features?","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250496306","doi":"https://doi.org/10.3115/v1/w14-1820","mag":"2250496306"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-1820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1820","pdf_url":"https://aclanthology.org/W14-1820.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-1820.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084812833","display_name":"Felice Dell\u2019Orletta\u22c4","orcid":"https://orcid.org/0000-0003-3454-9387"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT","NL"],"is_corresponding":false,"raw_author_name":"Felice Dell'Orletta","raw_affiliation_strings":["Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","\u2022 Department of Humanities Computing, University of Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"\u2022 Department of Humanities Computing, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075698724","display_name":"Martijn Wieling","orcid":"https://orcid.org/0000-0003-0434-1526"},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Martijn Wieling","raw_affiliation_strings":["Department of Quantitative Linguistics, University of Tbingen, Germany","Department of Quantitative Linguistics, University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative Linguistics, University of Tbingen, Germany","institution_ids":["https://openalex.org/I4210098931"]},{"raw_affiliation_string":"Department of Quantitative Linguistics, University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080111149","display_name":"Giulia Venturi\u22c4","orcid":"https://orcid.org/0000-0001-5849-0979"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT","NL"],"is_corresponding":false,"raw_author_name":"Giulia Venturi","raw_affiliation_strings":["Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","\u2022 Department of Humanities Computing, University of Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"\u2022 Department of Humanities Computing, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071401829","display_name":"Andrea Cimino","orcid":"https://orcid.org/0000-0003-0900-473X"},"institutions":[{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Andrea Cimino","raw_affiliation_strings":["Department of Quantitative Linguistics, University of Tbingen, Germany","Department of Quantitative Linguistics, University of T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative Linguistics, University of Tbingen, Germany","institution_ids":["https://openalex.org/I4210098931"]},{"raw_affiliation_string":"Department of Quantitative Linguistics, University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006938721","display_name":"Simonetta Montemagni\u22c4","orcid":"https://orcid.org/0000-0002-2953-8619"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"id":"https://openalex.org/I4210124522","display_name":"Institute for Computational Linguistics \u201cA. Zampolli\u201d","ror":"https://ror.org/028g3pe33","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210124522","https://openalex.org/I4210155236"]}],"countries":["IT","NL"],"is_corresponding":false,"raw_author_name":"Simonetta Montemagni","raw_affiliation_strings":["Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","\u2022 Department of Humanities Computing, University of Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto di Linguistica Computazionale \"Antonio Zampolli\" (ILC-CNR) ItaliaNLP Lab -www","institution_ids":["https://openalex.org/I4210124522"]},{"raw_affiliation_string":"\u2022 Department of Humanities Computing, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2746,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90617628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","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/T13629","display_name":"Text Readability and Simplification","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9769999980926514,"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/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.9635490775108337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341509103775024},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7731472849845886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7373970150947571},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6887134313583374},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6321710348129272},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6164258718490601},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5487455129623413},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5413515567779541},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48714491724967957},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47224491834640503},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.42272546887397766},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.419399231672287},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14647620916366577}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9635490775108337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341509103775024},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7731472849845886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7373970150947571},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6887134313583374},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6321710348129272},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6164258718490601},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5487455129623413},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5413515567779541},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48714491724967957},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47224491834640503},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.42272546887397766},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.419399231672287},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14647620916366577},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-1820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1820","pdf_url":"https://aclanthology.org/W14-1820.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/95b43d4b-72e7-40ed-bf8c-69be0798998c","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/95b43d4b-72e7-40ed-bf8c-69be0798998c","pdf_url":"https://pure.rug.nl/ws/files/14344750/W14_1820.pdf","source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"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":"Dell'Orletta, F, Wieling, M, Cimino, A, Venturi, G & Montemagni, S 2014, Assessing the readability of sentences : Which corpora and features? in Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications. ACL, Baltimore, USA, pp. 163-173.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire/95b43d4b-72e7-40ed-bf8c-69be0798998c","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/95b43d4b-72e7-40ed-bf8c-69be0798998c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"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":"Dell'Orletta, F, Wieling, M, Cimino, A, Venturi, G & Montemagni, S 2014, Assessing the readability of sentences : Which corpora and features? in Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications. ACL, Baltimore, USA, pp. 163-173.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-1820","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1820","pdf_url":"https://aclanthology.org/W14-1820.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250496306.pdf","grobid_xml":"https://content.openalex.org/works/W2250496306.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W164440181","https://openalex.org/W190511925","https://openalex.org/W610032745","https://openalex.org/W1491975949","https://openalex.org/W1508112475","https://openalex.org/W1509228788","https://openalex.org/W1528370852","https://openalex.org/W1562027891","https://openalex.org/W1590830694","https://openalex.org/W1591279088","https://openalex.org/W1599880985","https://openalex.org/W1615863701","https://openalex.org/W1655573795","https://openalex.org/W1680014149","https://openalex.org/W1950891412","https://openalex.org/W2019416425","https://openalex.org/W2031565004","https://openalex.org/W2045320784","https://openalex.org/W2092265701","https://openalex.org/W2097229755","https://openalex.org/W2099092905","https://openalex.org/W2110286374","https://openalex.org/W2117823388","https://openalex.org/W2129207541","https://openalex.org/W2133944470","https://openalex.org/W2140676672","https://openalex.org/W2140798110","https://openalex.org/W2150783756","https://openalex.org/W2153081451","https://openalex.org/W2158437734","https://openalex.org/W2161047600","https://openalex.org/W2250104175","https://openalex.org/W2250504379","https://openalex.org/W2251661103","https://openalex.org/W2252010905","https://openalex.org/W2325944896","https://openalex.org/W2333855391","https://openalex.org/W2398973842","https://openalex.org/W2797865084","https://openalex.org/W4388123074"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2972807713","https://openalex.org/W4285478380","https://openalex.org/W4315704968","https://openalex.org/W2100255360","https://openalex.org/W2064074028"],"abstract_inverted_index":{"The":[0],"paper":[1],"investigates":[2],"the":[3,34,42,45,64,86,95],"problem":[4],"of":[5,44,66,97,107],"sentence":[6,51],"readability":[7,55,96],"assessment,":[8],"which":[9],"is":[10,99],"modelled":[11],"as":[12],"a":[13,17,100,104],"classification":[14],"task,":[15,102],"with":[16,31],"specific":[18],"view":[19],"to":[20,36,49,83,85],"text":[21],"simplification.":[22],"In":[23],"particular,":[24],"it":[25,90],"addresses":[26],"two":[27],"open":[28],"issues":[29],"connected":[30],"it,":[32],"i.e.":[33],"corpora":[35],"be":[37],"used":[38,82],"for":[39,59],"training,":[40],"and":[41,69,77],"identification":[43],"most":[46,87],"effective":[47],"features":[48],"determine":[50],"readability.":[52],"An":[53],"existing":[54],"assessment":[56],"tool":[57],"developed":[58],"Italian":[60],"was":[61,81],"specialized":[62],"at":[63],"level":[65],"training":[67],"corpus":[68],"learning":[70],"algorithm.":[71],"A":[72],"maximum":[73],"entropy-based":[74],"feature":[75],"selection":[76],"ranking":[78],"algorithm":[79],"(grafting)":[80],"identify":[84],"relevant":[88],"features:":[89],"turned":[91],"out":[92],"that":[93],"assessing":[94],"sentences":[98],"complex":[101],"requiring":[103],"high":[105],"number":[106],"features,":[108],"mainly":[109],"syntactic":[110],"ones.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}