{"id":"https://openalex.org/W2251127293","doi":"https://doi.org/10.3115/v1/w14-1210","title":"An Open Corpus of Everyday Documents for Simplification Tasks","display_name":"An Open Corpus of Everyday Documents for Simplification Tasks","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251127293","doi":"https://doi.org/10.3115/v1/w14-1210","mag":"2251127293"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-1210","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1210","pdf_url":"https://aclanthology.org/W14-1210.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 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-1210.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008335823","display_name":"David Pellow","orcid":"https://orcid.org/0000-0002-6296-5209"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Pellow","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University Pittsburgh PA USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University Pittsburgh PA USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxine Eskenazi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University Pittsburgh PA USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University Pittsburgh PA USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008335823"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.96,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92549987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"93"},"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":0.9886999726295471,"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":0.9689000248908997,"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":0.8497151136398315},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.761589765548706},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6550076603889465},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5960623621940613},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4981071949005127},{"id":"https://openalex.org/keywords/everyday-life","display_name":"Everyday life","score":0.4904925227165222},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.44529324769973755},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.441213995218277},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4361977279186249},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42582929134368896},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14116540551185608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8497151136398315},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.761589765548706},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6550076603889465},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5960623621940613},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4981071949005127},{"id":"https://openalex.org/C2779018934","wikidata":"https://www.wikidata.org/wiki/Q1129653","display_name":"Everyday life","level":2,"score":0.4904925227165222},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.44529324769973755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.441213995218277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4361977279186249},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42582929134368896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14116540551185608},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":2,"locations":[{"id":"doi:10.3115/v1/w14-1210","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1210","pdf_url":"https://aclanthology.org/W14-1210.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 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.4093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.4093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-1210.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-1210","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1210","pdf_url":"https://aclanthology.org/W14-1210.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 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251127293.pdf","grobid_xml":"https://content.openalex.org/works/W2251127293.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W26331037","https://openalex.org/W33677238","https://openalex.org/W44526853","https://openalex.org/W170711724","https://openalex.org/W175030052","https://openalex.org/W1419238556","https://openalex.org/W1507711477","https://openalex.org/W1528370852","https://openalex.org/W1704713987","https://openalex.org/W1838004822","https://openalex.org/W2000332471","https://openalex.org/W2042262613","https://openalex.org/W2061235289","https://openalex.org/W2104907655","https://openalex.org/W2109802560","https://openalex.org/W2119954850","https://openalex.org/W2133944470","https://openalex.org/W2154624463","https://openalex.org/W2163361328","https://openalex.org/W2250762319","https://openalex.org/W2251386396","https://openalex.org/W2251916238","https://openalex.org/W2252150696","https://openalex.org/W2401830275","https://openalex.org/W2581101955"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"In":[0,40],"recent":[1],"years":[2],"interest":[3],"in":[4,156],"creating":[5],"statistical":[6],"automated":[7],"text":[8],"simplification":[9,66,157],"systems":[10,16,67],"has":[11],"increased.":[12],"Many":[13],"of":[14,21,53,65,79,90,116,128,153,158],"these":[15,135],"have":[17,94],"used":[18],"parallel":[19],"corpora":[20],"articles":[22],"taken":[23],"from":[24,30,102],"Wikipedia":[25,28,32,38],"and":[26,35,63,86,110],"Simple":[27,31,37],"or":[29],"revision":[33],"histories":[34],"generate":[36,132],"articles.":[39],"this":[41,81],"work":[42,124],"we":[43,93],"motivate":[44],"the":[45,61,87,126,139,151],"need":[46],"to":[47,131,150],"construct":[48],"a":[49,76,114],"large,":[50],"accessible":[51],"corpus":[52,82,89,145],"everyday":[54,70,91,100,159],"documents":[55,71,92,101],"along":[56],"with":[57],"their":[58],"simplifications":[59,133],"for":[60,134,141],"development":[62],"evaluation":[64],"that":[68],"make":[69],"more":[72],"accessible.":[73],"We":[74,120],"present":[75],"detailed":[77],"description":[78],"what":[80],"will":[83,147],"look":[84],"like":[85],"basic":[88],"already":[95],"collected.":[96],"This":[97,137],"latter":[98],"contains":[99,113],"many":[103],"domains":[104],"including":[105],"driver's":[106],"licensing,":[107],"government":[108],"aid":[109],"banking.":[111],"It":[112],"total":[115],"over":[117],"120,000":[118],"sentences.":[119],"describe":[121],"our":[122,142],"preliminary":[123],"evaluating":[125],"feasibility":[127],"using":[129],"crowdsourcing":[130],"documents.":[136,160],"is":[138],"basis":[140],"future":[143],"extended":[144],"which":[146],"be":[148],"available":[149],"community":[152],"researchers":[154],"interested":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}