{"id":"https://openalex.org/W2105715031","doi":"https://doi.org/10.1145/1060745.1060845","title":"An adaptive, fast, and safe XML parser based on byte sequences memorization","display_name":"An adaptive, fast, and safe XML parser based on byte sequences memorization","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2105715031","doi":"https://doi.org/10.1145/1060745.1060845","mag":"2105715031"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015220324","display_name":"Toshiro Takase","orcid":"https://orcid.org/0000-0001-9504-9867"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toshiro Takase","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006016101","display_name":"Hisashi Miyashita","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hisashi MIYASHITA","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011886931","display_name":"Toyotaro Suzumura","orcid":"https://orcid.org/0000-0001-6412-8386"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toyotaro Suzumura","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049672783","display_name":"Michiaki Tatsubori","orcid":"https://orcid.org/0000-0003-2537-700X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiaki Tatsubori","raw_affiliation_strings":["IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Tokyo Research Laboratory, Yamato Kanagawa, Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"692","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8652608394622803},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7091529369354248},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6440458297729492},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.5858186483383179},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5772196054458618},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4820864796638489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46191835403442383},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.4380713999271393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35204991698265076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3221837282180786},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.3124179244041443},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22307458519935608},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.19426286220550537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07731232047080994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652608394622803},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7091529369354248},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6440458297729492},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.5858186483383179},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5772196054458618},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4820864796638489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46191835403442383},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.4380713999271393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35204991698265076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3221837282180786},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.3124179244041443},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22307458519935608},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.19426286220550537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07731232047080994},{"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:10.1145/1060745.1060845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.8126","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.8126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p692.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W89823361","https://openalex.org/W174869497","https://openalex.org/W178105064","https://openalex.org/W1575689155","https://openalex.org/W1609518033","https://openalex.org/W1628216882","https://openalex.org/W1717406413","https://openalex.org/W1819656317","https://openalex.org/W1965014786","https://openalex.org/W1993865637","https://openalex.org/W2098462978","https://openalex.org/W2111617062","https://openalex.org/W2137847645","https://openalex.org/W2141378275","https://openalex.org/W2141641405","https://openalex.org/W2150610576","https://openalex.org/W2159400364","https://openalex.org/W2543163441"],"related_works":["https://openalex.org/W1972245780","https://openalex.org/W2347775463","https://openalex.org/W2347497444","https://openalex.org/W2024164996","https://openalex.org/W2090406160","https://openalex.org/W2314138807","https://openalex.org/W2386420321","https://openalex.org/W2047342127","https://openalex.org/W2381329604","https://openalex.org/W2354363460"],"abstract_inverted_index":{"XML":[0,30,35,42,75,115],"(Extensible":[1],"Markup":[2],"Language)":[3],"processing":[4,28],"can":[5],"incur":[6],"significant":[7],"runtime":[8],"overhead":[9],"in":[10,45,143,153],"XML-based":[11],"infrastructural":[12],"middleware":[13],"such":[14],"as":[15,37],"Web":[16,128],"service":[17],"application":[18],"servers.":[19],"This":[20],"paper":[21,47],"proposes":[22],"a":[23,33,38,144,154],"novel":[24],"mechanism":[25],"for":[26,114],"efficiently":[27],"similar":[29],"documents.":[31,97],"Given":[32],"new":[34],"document":[36,56,76],"byte":[39],"sequence,":[40],"the":[41,55,94,101,106,111],"parser":[43,65,103],"proposed":[44,102],"this":[46],"normally":[48],"avoids":[49],"syntactic":[50],"analysis":[51],"but":[52],"simply":[53],"matches":[54],"with":[57,105,124],"previously":[58],"processed":[59],"ones,":[60],"reusing":[61],"those":[62],"results.":[63],"Our":[64,98],"is":[66],"adaptive":[67],"since":[68,88],"it":[69,79,85,136],"partially":[70],"parses":[71,138],"and":[72,148],"then":[73],"remembers":[74],"fragments":[77],"that":[78],"has":[80],"not":[81],"met":[82],"before.":[83],"Moreover,":[84],"processes":[86],"safely":[87],"its":[89],"partial":[90],"parsing":[91],"correctly":[92],"checks":[93],"well-formedness":[95],"of":[96,100,110],"implementation":[99],"complies":[104],"JSR":[107],"63":[108],"standard":[109],"Java":[112],"API":[113],"Processing":[116],"(JAXP)":[117],"1.1":[118],"specification.":[119],"We":[120],"evaluated":[121],"Deltarser":[122],"performance":[123],"messages":[125],"using":[126],"Google":[127],"services.":[129],"Comparing":[130],"to":[131],"Piccolo":[132],"(and":[133],"Apache":[134],"Xerces),":[135],"effectively":[137],"35":[139],"%":[140,150],"(106%)":[141],"faster":[142,152],"server-side":[145],"use-case":[146,156],"scenario,":[147],"73":[149],"(126%)":[151],"client-side":[155],"scenario.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
