{"id":"https://openalex.org/W2077680785","doi":"https://doi.org/10.1145/1284420.1284468","title":"Structure and content analysis for html medical articles","display_name":"Structure and content analysis for html medical articles","publication_year":2007,"publication_date":"2007-08-28","ids":{"openalex":"https://openalex.org/W2077680785","doi":"https://doi.org/10.1145/1284420.1284468","mag":"2077680785"},"language":"en","primary_location":{"id":"doi:10.1145/1284420.1284468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1284420.1284468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101585404","display_name":"Jie Zou","orcid":"https://orcid.org/0000-0003-2359-6401"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Zou","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101509629","display_name":"Daniel Le","orcid":"https://orcid.org/0000-0002-0220-6366"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Le","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103701816","display_name":"George R. Thoma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George R. Thoma","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD","institution_ids":["https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210109390"],"apc_list":null,"apc_paid":null,"fwci":2.4879,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91579539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.992900013923645,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9830999970436096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802308797836304},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6517142653465271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5917971730232239},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5788262486457825},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5748218297958374},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.574256956577301},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5448085069656372},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5250382423400879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33276212215423584},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32539916038513184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3023824393749237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06772011518478394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802308797836304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6517142653465271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5917971730232239},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5788262486457825},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5748218297958374},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.574256956577301},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5448085069656372},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5250382423400879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33276212215423584},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32539916038513184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3023824393749237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06772011518478394},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1284420.1284468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1284420.1284468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.6309","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.6309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lhncbc.nlm.nih.gov/lhc/docs/published/2007/pub2007082.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314788","display_name":"Lister Hill National Center for Biomedical Communications","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W193121434","https://openalex.org/W2019264297","https://openalex.org/W2070030212","https://openalex.org/W2118020653","https://openalex.org/W2142384583","https://openalex.org/W2162565240","https://openalex.org/W2166419939"],"related_works":["https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W2373402338","https://openalex.org/W2114620981","https://openalex.org/W4302086745","https://openalex.org/W2626998250","https://openalex.org/W2411679502","https://openalex.org/W2184959150","https://openalex.org/W2039658447","https://openalex.org/W1987716395"],"abstract_inverted_index":{"We":[0],"describe":[1],"ongoing":[2],"research":[3],"on":[4,31],"segmenting":[5],"and":[6],"labeling":[7],"HTML":[8,19,32,59],"medical":[9],"journal":[10,53],"articles.":[11],"In":[12],"contrast":[13],"to":[14,28],"existing":[15],"approaches":[16],"in":[17,47],"which":[18],"tags":[20],"usually":[21],"serve":[22],"as":[23],"strong":[24],"indicators,":[25],"we":[26,55],"seek":[27],"minimize":[29],"dependence":[30],"tags.":[33],"Designing":[34],"logical":[35,72],"component":[36],"models":[37],"for":[38],"general":[39],"Web":[40],"pages":[41],"is":[42],"a":[43,63],"challenging":[44],"task.":[45],"However,":[46],"the":[48,58],"narrow":[49],"domain":[50],"of":[51],"online":[52],"articles,":[54],"show":[56],"that":[57],"document,":[60],"modeled":[61],"with":[62],"Hidden":[64],"Markov":[65],"Model,":[66],"can":[67],"be":[68],"accurately":[69],"segmented":[70],"into":[71],"zones.":[73]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
