{"id":"https://openalex.org/W2963308332","doi":"https://doi.org/10.1145/3132847.3133104","title":"Language Modeling by Clustering with Word Embeddings for Text Readability Assessment","display_name":"Language Modeling by Clustering with Word Embeddings for Text Readability Assessment","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2963308332","doi":"https://doi.org/10.1145/3132847.3133104","mag":"2963308332"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3133104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:41531368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029707299","display_name":"Miriam Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Miriam Cha","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012323997","display_name":"Youngjune Gwon","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngjune Gwon","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075019408","display_name":"H. T. Kung","orcid":"https://orcid.org/0000-0002-9214-492X"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. T. Kung","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029707299"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":2.7303,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.92669846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2003","last_page":"2006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","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/T13629","display_name":"Text Readability and Simplification","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.9840999841690063,"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":0.7981981039047241},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.7620266675949097},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7439904808998108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7116111516952515},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.708655595779419},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6298989057540894},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.515995979309082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5016279220581055},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.448099821805954},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4184260666370392},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4182548224925995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12958309054374695},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11768171191215515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981981039047241},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.7620266675949097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7439904808998108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7116111516952515},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.708655595779419},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6298989057540894},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.515995979309082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5016279220581055},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.448099821805954},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4184260666370392},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4182548224925995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12958309054374695},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11768171191215515},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1145/3132847.3133104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:dash.harvard.edu:1/41531368","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:41531368","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:dash.harvard.edu:1/41531368","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:41531368","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1505680913","https://openalex.org/W1507711477","https://openalex.org/W1520424381","https://openalex.org/W1669955980","https://openalex.org/W1967390364","https://openalex.org/W1982643343","https://openalex.org/W2062585132","https://openalex.org/W2109802560","https://openalex.org/W2118585731","https://openalex.org/W2121227244","https://openalex.org/W2131744502","https://openalex.org/W2143017621","https://openalex.org/W2153081451","https://openalex.org/W2158139315","https://openalex.org/W2182333754","https://openalex.org/W2252206005","https://openalex.org/W2480068437","https://openalex.org/W2493916176","https://openalex.org/W2510403706","https://openalex.org/W2882319491","https://openalex.org/W2950577311","https://openalex.org/W2953320089","https://openalex.org/W2998704965","https://openalex.org/W3001645704","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W127573234","https://openalex.org/W2125145484","https://openalex.org/W2984927260","https://openalex.org/W159132833","https://openalex.org/W4385572889","https://openalex.org/W2739504579","https://openalex.org/W4307205354","https://openalex.org/W3102113045","https://openalex.org/W2819344641","https://openalex.org/W4385571594"],"abstract_inverted_index":{"We":[0,32,105],"present":[1],"a":[2,48],"clustering-based":[3,89],"language":[4,90],"model":[5,91],"using":[6,76,117],"word":[7,22,30,37],"embeddings":[8,23,38],"for":[9,21,53,98],"text":[10,54],"readability":[11,103],"prediction.":[12,104],"Presumably,":[13],"an":[14],"Euclidean":[15],"semantic":[16,50,115],"space":[17,42,51],"hypothesis":[18],"holds":[19],"true":[20],"whose":[24],"training":[25],"is":[26],"done":[27],"by":[28,57],"observing":[29],"co-occurrences.":[31],"argue":[33],"that":[34,83,123],"clustering":[35],"with":[36],"in":[39,47,60,102],"the":[40,77,84,94,99,108,118],"metric":[41],"should":[43],"yield":[44],"feature":[45],"representations":[46],"higher":[49],"appropriate":[52],"regression.":[55],"Also,":[56],"representing":[58],"features":[59,85,125],"terms":[61],"of":[62,70,110],"histograms,":[63],"our":[64,88,124],"approach":[65],"can":[66],"naturally":[67],"address":[68],"documents":[69],"varying":[71],"lengths.":[72],"An":[73],"empirical":[74],"evaluation":[75],"Common":[78],"Core":[79],"Standards":[80],"corpus":[81,101,120],"reveals":[82],"formed":[86],"on":[87,114],"significantly":[92],"improve":[93],"previously":[95],"known":[96],"results":[97],"same":[100],"also":[106],"evaluate":[107],"task":[109],"sentence":[111],"matching":[112,129],"based":[113],"relatedness":[116],"Wiki-SimpleWiki":[119],"and":[121],"find":[122],"lead":[126],"to":[127],"superior":[128],"performance.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}