{"id":"https://openalex.org/W3197759495","doi":"https://doi.org/10.1145/3471158.3472234","title":"Can Language Models Identify Wikipedia Articles with Readability and Style Issues?","display_name":"Can Language Models Identify Wikipedia Articles with Readability and Style Issues?","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3197759495","doi":"https://doi.org/10.1145/3471158.3472234","mag":"3197759495"},"language":"en","primary_location":{"id":"doi:10.1145/3471158.3472234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3471158.3472234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10138/352578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693653","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-4393-1791"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007118986","display_name":"Alan Medlar","orcid":"https://orcid.org/0000-0002-5139-9483"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alan Medlar","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001270670","display_name":"Dorota G\u0142owacka","orcid":"https://orcid.org/0000-0001-7008-3380"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dorota Glowacka","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":0.5261,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72054381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9922999739646912,"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":0.9883000254631042,"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/perplexity","display_name":"Perplexity","score":0.9852004051208496},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.9232296943664551},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7537064552307129},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6636483073234558},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.5894239544868469},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5570192337036133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5481661558151245},{"id":"https://openalex.org/keywords/narrativity","display_name":"Narrativity","score":0.5456534028053284},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5205122828483582},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4751862585544586},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4665149450302124},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.45722925662994385},{"id":"https://openalex.org/keywords/writing-style","display_name":"Writing style","score":0.44156602025032043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39134666323661804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39114314317703247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30823415517807007},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.16454243659973145},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08930730819702148}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9852004051208496},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9232296943664551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537064552307129},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6636483073234558},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.5894239544868469},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5570192337036133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5481661558151245},{"id":"https://openalex.org/C2780787791","wikidata":"https://www.wikidata.org/wiki/Q6966232","display_name":"Narrativity","level":3,"score":0.5456534028053284},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5205122828483582},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4751862585544586},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4665149450302124},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.45722925662994385},{"id":"https://openalex.org/C13622073","wikidata":"https://www.wikidata.org/wiki/Q2243831","display_name":"Writing style","level":2,"score":0.44156602025032043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39134666323661804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39114314317703247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30823415517807007},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.16454243659973145},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08930730819702148},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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:10.1145/3471158.3472234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3471158.3472234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/352578","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/352578","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:helda.helsinki.fi:10138/352578","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/352578","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1481128830","https://openalex.org/W1509228788","https://openalex.org/W1602368597","https://openalex.org/W1972644898","https://openalex.org/W1989304522","https://openalex.org/W2043055815","https://openalex.org/W2059398918","https://openalex.org/W2065100127","https://openalex.org/W2462263535","https://openalex.org/W2567547739","https://openalex.org/W2737145921","https://openalex.org/W2806183494","https://openalex.org/W2955427418","https://openalex.org/W4206765718","https://openalex.org/W4238277744","https://openalex.org/W6664540657"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"Wikipedia":[0,28,87],"is":[1],"frequently":[2],"criticised":[3],"for":[4,118],"having":[5],"poor":[6],"readability":[7],"and":[8,51],"style":[9],"issues.":[10],"In":[11],"this":[12,40],"article,":[13],"we":[14],"investigate":[15],"using":[16,42],"GPT-2,":[17],"a":[18],"neural":[19],"language":[20,52],"model,":[21],"to":[22,62,80,115,122],"identify":[23],"poorly":[24],"written":[25],"text":[26,46,81,99],"in":[27,86,125],"by":[29,32,91],"ranking":[30,41],"documents":[31],"their":[33],"perplexity.":[34],"We":[35,54,89],"evaluated":[36],"the":[37,74,101,111],"properties":[38],"of":[39,45,110],"human":[43],"assessments":[44],"quality,":[47],"including":[48],"readability,":[49],"narrativity":[50],"use.":[53],"demonstrate":[55],"that":[56,93,113],"GPT-2":[57],"perplexity":[58,103],"scores":[59],"correlate":[60],"moderately":[61],"strongly":[63],"with":[64,69,100],"narrativity,":[65],"but":[66],"only":[67],"weakly":[68],"reading":[70],"comprehension":[71],"scores.":[72,104],"Importantly,":[73],"model":[75],"reflects":[76],"even":[77],"small":[78],"improvements":[79],"as":[82],"would":[83],"be":[84,116,123],"seen":[85],"edits.":[88],"conclude":[90],"highlighting":[92],"Wikipedia's":[94],"featured":[95],"articles":[96],"counter-intuitively":[97],"contain":[98],"highest":[102],"However,":[105],"these":[106],"examples":[107],"highlight":[108],"many":[109],"complexities":[112],"need":[114],"resolved":[117],"such":[119],"an":[120],"approach":[121],"used":[124],"practice.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
