{"id":"https://openalex.org/W4404782380","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.958","title":"MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain","display_name":"MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782380","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.958","pmid":"https://pubmed.ncbi.nlm.nih.gov/40612445"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.958","pdf_url":"https://aclanthology.org/2024.emnlp-main.958.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.958.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067502052","display_name":"Chao Jiang","orcid":"https://orcid.org/0000-0002-7123-6702"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Jiang","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070905937","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7044-3232"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.0668,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80239189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2024","issue":null,"first_page":"17293","last_page":"17319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9187999963760376,"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/readability","display_name":"Readability","score":0.9056598544120789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7885206937789917},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5931520462036133},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5685433149337769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5168105363845825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40599992871284485},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34539783000946045},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24024447798728943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08104166388511658}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9056598544120789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885206937789917},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5931520462036133},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5685433149337769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5168105363845825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40599992871284485},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34539783000946045},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24024447798728943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08104166388511658},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.958","pdf_url":"https://aclanthology.org/2024.emnlp-main.958.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmid:40612445","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40612445","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12225841","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12225841","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12225841/pdf/nihms-2092973.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Conf Empir Methods Nat Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.958","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.958","pdf_url":"https://aclanthology.org/2024.emnlp-main.958.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 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3596567917","display_name":"CAREER: An Integrated Framework for Controllable Text Generation","funder_award_id":"2144493","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3634950783","display_name":null,"funder_award_id":"R01 LM014600","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7403748957","display_name":"AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups (AI-CARING)","funder_award_id":"2112633","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782380.pdf","grobid_xml":"https://content.openalex.org/works/W4404782380.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W133394232"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W2064074028","https://openalex.org/W2369835347"],"abstract_inverted_index":{"Medical":[0],"texts":[1],"are":[2],"notoriously":[3],"challenging":[4],"to":[5],"read.":[6],"Properly":[7],"measuring":[8],"their":[9,146],"readability":[10,30,52,98,141],"is":[11],"the":[12,33,101,134,155],"first":[13],"step":[14],"towards":[15],"making":[16],"them":[17],"more":[18],"accessible.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,91,126],"present":[24],"a":[25,43,130],"systematic":[26],"study":[27],"on":[28],"fine-grained":[29,55,122],"measurements":[31],"in":[32],"medical":[34,102],"domain":[35,103],"at":[36],"both":[37],"sentence-level":[38,97],"and":[39,54,66,79,83,93,109,157],"span-level.":[40],"We":[41,151],"introduce":[42],"new":[44],"dataset":[45,156],"MedReadMe,":[46],"which":[47,74,105],"consists":[48],"of":[49,136],"manually":[50],"annotated":[51],"ratings":[53],"complex":[56,81,123],"span":[57,124],"annotation":[58],"for":[59,100],"4,520":[60],"sentences,":[61],"featuring":[62],"two":[63],"novel":[64],"\"Google-Easy\"":[65],"\"Google-Hard\"":[67],"categories.":[68],"It":[69],"supports":[70],"our":[71,88,121],"quantitative":[72],"analysis,":[73],"covers":[75],"650":[76],"linguistic":[77],"features":[78],"automatic":[80],"word":[82],"jargon":[84,137],"identification.":[85],"Enabled":[86],"by":[87,120],"high-quality":[89],"annotation,":[90,125],"benchmark":[92],"improve":[94,145],"several":[95],"state-of-the-art":[96],"metrics":[99],"specifically,":[104],"include":[106],"unsupervised,":[107],"supervised,":[108],"prompting-based":[110],"methods":[111],"using":[112],"recently":[113],"developed":[114],"large":[115],"language":[116],"models":[117],"(LLMs).":[118],"Informed":[119],"find":[127],"that":[128],"adding":[129],"single":[131],"feature,":[132],"capturing":[133],"number":[135],"spans,":[138],"into":[139],"existing":[140],"formulas":[142],"can":[143],"significantly":[144],"correlation":[147],"with":[148],"human":[149],"judgments.":[150],"will":[152],"publicly":[153],"release":[154],"code.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}