{"id":"https://openalex.org/W2295223726","doi":"https://doi.org/10.15439/2015f380","title":"The Serialization of Heterogeneous Documents","display_name":"The Serialization of Heterogeneous Documents","publication_year":2015,"publication_date":"2015-10-11","ids":{"openalex":"https://openalex.org/W2295223726","doi":"https://doi.org/10.15439/2015f380","mag":"2295223726"},"language":"en","primary_location":{"id":"doi:10.15439/2015f380","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f380","pdf_url":"https://annals-csis.org/proceedings/2015/pliks/380.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2015/pliks/380.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109947289","display_name":"Peter J. Hampton","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peter John Hampton","raw_affiliation_strings":["Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019839723","display_name":"William Blackburn","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William Blackburn","raw_affiliation_strings":["Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114106246","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8356-1975"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Applications Research Group Ulster University, Jordanstown United Kingdom, BT37 0QB","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109947289"],"corresponding_institution_ids":["https://openalex.org/I138801177"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08087947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/serialization","display_name":"Serialization","score":0.8803062438964844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8786221742630005},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6880790591239929},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.64739990234375},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6288079023361206},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5824316740036011},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5398271679878235},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5264347791671753},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5125996470451355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4680086672306061},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.42624717950820923},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3823452591896057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.322192907333374},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21120068430900574},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13004446029663086},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.09339821338653564}],"concepts":[{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.8803062438964844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8786221742630005},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6880790591239929},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.64739990234375},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6288079023361206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5824316740036011},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5398271679878235},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5264347791671753},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5125996470451355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4680086672306061},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.42624717950820923},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3823452591896057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.322192907333374},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21120068430900574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13004446029663086},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.09339821338653564},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.15439/2015f380","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f380","pdf_url":"https://annals-csis.org/proceedings/2015/pliks/380.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:876096c67be841a4a6a1c229617c8065","is_oa":true,"landing_page_url":"https://doaj.org/article/876096c67be841a4a6a1c229617c8065","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"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":"Annals of computer science and information systems, Vol 6, Pp 25-30 (2015)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2015f380","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f380","pdf_url":"https://annals-csis.org/proceedings/2015/pliks/380.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2295223726.pdf","grobid_xml":"https://content.openalex.org/works/W2295223726.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W178986155","https://openalex.org/W348693189","https://openalex.org/W1544590421","https://openalex.org/W1910748762","https://openalex.org/W2012275481","https://openalex.org/W2082190528","https://openalex.org/W2107092590","https://openalex.org/W2121157913","https://openalex.org/W2123442489","https://openalex.org/W2143017621","https://openalex.org/W2164946090","https://openalex.org/W2577020101","https://openalex.org/W2953320089","https://openalex.org/W3170282186","https://openalex.org/W6653255092","https://openalex.org/W6796313370","https://openalex.org/W6814661027","https://openalex.org/W6983682869"],"related_works":["https://openalex.org/W4231356583","https://openalex.org/W1593760324","https://openalex.org/W2376159383","https://openalex.org/W2351439380","https://openalex.org/W2899905671","https://openalex.org/W4390136247","https://openalex.org/W2365228680","https://openalex.org/W2131622620","https://openalex.org/W2362327801","https://openalex.org/W2977327189"],"abstract_inverted_index":{"Tasks":[0],"involving":[1],"the":[2,83,96,100],"analysis":[3],"of":[4,15,56,112],"natural":[5],"language":[6],"are":[7],"typically":[8],"conducted":[9],"on":[10],"a":[11,23,54,66,75,91,109],"corpus":[12],"or":[13],"corpora":[14],"plain":[16],"text.":[17],"However,":[18],"it":[19],"is":[20,25],"rare":[21],"that":[22,49,79,104],"document":[24,84],"unstructured":[26],"and":[27,39,46,87,99],"freeform":[28],"in":[29,53],"its":[30],"entirety.":[31],"Documents":[32],"such":[33],"as":[34],"corporate":[35],"disclosures,":[36],"medical":[37],"journals":[38],"other":[40],"knowledge":[41],"rich":[42],"archive":[43],"contain":[44],"structured":[45],"loosely-structured":[47],"information":[48],"can":[50],"be":[51],"used":[52],"variety":[55],"important":[57],"text":[58],"mining":[59],"tasks.":[60],"In":[61],"this":[62],"paper":[63],"we":[64],"propose":[65],"syntactical":[67],"preprocessing":[68],"architecture":[69],"to":[70,74,81,108],"serialize":[71],"presentationoriented":[72],"documents":[73],"machine":[76],"readable":[77],"format":[78],"aspires":[80],"preserve":[82],"structure,":[85],"contents":[86],"metadata.":[88],"We":[89],"introduce":[90],"hybrid":[92],"pipeline":[93],"architecture,":[94],"discussing":[95],"various":[97],"processes":[98],"future":[101],"research":[102],"direction":[103],"could":[105],"potentially":[106],"lead":[107],"holistic":[110],"representation":[111],"heterogeneous":[113],"documents.":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
