{"id":"https://openalex.org/W1985703572","doi":"https://doi.org/10.1145/2034691.2034707","title":"Developer-friendly annotation-based HTML-to-XML transformation technology","display_name":"Developer-friendly annotation-based HTML-to-XML transformation technology","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W1985703572","doi":"https://doi.org/10.1145/2034691.2034707","mag":"1985703572"},"language":"en","primary_location":{"id":"doi:10.1145/2034691.2034707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th 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/A5044829425","display_name":"Lendle Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I50519452","display_name":"Lunghwa University of Science and Technology","ror":"https://ror.org/001y2wd07","country_code":"TW","type":"education","lineage":["https://openalex.org/I50519452"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Lendle Chun-Hsiung Tseng","raw_affiliation_strings":["Lunghwa University of Science and Technology, Taoyuan, Taiwan Roc","Lunghwa University of Science and Technology, Taoyuan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Lunghwa University of Science and Technology, Taoyuan, Taiwan Roc","institution_ids":["https://openalex.org/I50519452"]},{"raw_affiliation_string":"Lunghwa University of Science and Technology, Taoyuan, Taiwan, ROC","institution_ids":["https://openalex.org/I50519452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044829425"],"corresponding_institution_ids":["https://openalex.org/I50519452"],"apc_list":null,"apc_paid":null,"fwci":1.49497299,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87306386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8656051754951477},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7504457831382751},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6205427646636963},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5579297542572021},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.5529702305793762},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.5507451891899109},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5189856886863708},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5094230771064758},{"id":"https://openalex.org/keywords/web-design","display_name":"Web design","score":0.44506901502609253},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4390217065811157},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.424085408449173},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.4231695830821991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8656051754951477},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7504457831382751},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6205427646636963},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5579297542572021},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.5529702305793762},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.5507451891899109},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5189856886863708},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5094230771064758},{"id":"https://openalex.org/C521306242","wikidata":"https://www.wikidata.org/wiki/Q190637","display_name":"Web design","level":3,"score":0.44506901502609253},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4390217065811157},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.424085408449173},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.4231695830821991}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2034691.2034707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1992981000","https://openalex.org/W2024442287","https://openalex.org/W2069388662","https://openalex.org/W2071628657","https://openalex.org/W2072936489","https://openalex.org/W2134150392","https://openalex.org/W2145404631"],"related_works":["https://openalex.org/W1583761149","https://openalex.org/W2100071482","https://openalex.org/W980488187","https://openalex.org/W1782470797","https://openalex.org/W1968141708","https://openalex.org/W2792695632","https://openalex.org/W3025289787","https://openalex.org/W2559599206","https://openalex.org/W188332989","https://openalex.org/W3089257250"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,7,24,75,90,98,104,136],"amount":[2],"of":[3,101],"information":[4,22,33,67],"accessible":[5],"on":[6,23,176],"web":[8,12,36,40,69,140,148,151],"is":[9,27,48,54,122,126],"huge.":[10],"Although":[11],"users":[13],"today":[14],"expect":[15],"a":[16,50],"more":[17,94],"integrated":[18],"way":[19],"to":[20,31,92,146],"access":[21],"web,":[25],"it":[26],"still":[28],"rather":[29],"difficult":[30],"\"integrate\"":[32],"from":[34,68],"different":[35],"sites":[37],"since":[38],"most":[39],"pages":[41,152],"are":[42,60,167],"authored":[43],"in":[44,133],"HTML":[45,102],"format,":[46],"which":[47,166],"actually":[49],"presentation-oriented":[51],"language":[52],"and":[53,108,131,161],"usually":[55],"considered":[56],"unstructured.":[57],"Today,":[58],"there":[59],"many":[61],"research":[62],"works":[63,72],"aiming":[64],"at":[65],"extracting":[66,76],"pages.":[70,149],"Existing":[71],"typically":[73],"transform":[74],"results":[77,91],"into":[78,163],"structured":[79],"or":[80],"semi-structured":[81],"data":[82],"formats,":[83],"thus":[84,171],"other":[85],"applications":[86],"can":[87,109,153,172],"further":[88],"process":[89,106],"discover":[93],"useful":[95],"information.":[96],"Nevertheless,":[97],"unstructured":[99],"nature":[100],"makes":[103],"transformation":[105],"complex":[107],"hardly":[110],"be":[111,155,173],"widely":[112],"adopted.":[113],"In":[114],"this":[115],"paper,":[116],"an":[117],"annotation-based":[118],"HTML-to-XML":[119],"ransformation":[120],"technology":[121],"proposed.":[123],"The":[124],"mechanism":[125],"developed":[127,174],"with":[128],"both":[129],"usability":[130],"simplicity":[132],"mind.":[134],"With":[135],"proposed":[137],"mechanism,":[138],"ordinary":[139],"site":[141],"developers":[142],"simply":[143],"add":[144],"annotations":[145],"their":[147],"Annotated":[150],"then":[154],"processed":[156],"by":[157],"our":[158,177],"software":[159],"libraries":[160],"transformed":[162],"XML":[164],"documents,":[165],"machine-understandable.":[168],"Software":[169],"agents":[170],"based":[175],"technology.":[178]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
