{"id":"https://openalex.org/W2023515034","doi":"https://doi.org/10.1145/1277741.1277877","title":"Where to start reading a textual XML document?","display_name":"Where to start reading a textual XML document?","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2023515034","doi":"https://doi.org/10.1145/1277741.1277877","mag":"2023515034"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5044511901","display_name":"Jaap Kamps","orcid":"https://orcid.org/0000-0002-6614-0087"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaap Kamps","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067054454","display_name":"Marijn Koolen","orcid":"https://orcid.org/0000-0002-0301-2029"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marijn Koolen","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002597222","display_name":"Mounia Lalmas","orcid":"https://orcid.org/0000-0002-3531-3096"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mounia Lalmas","raw_affiliation_strings":["Queen Mary: University of London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary: University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0907,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76546416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"723","last_page":"724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9993000030517578,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8343642950057983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7135394215583801},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6268117427825928},{"id":"https://openalex.org/keywords/well-formed-document","display_name":"Well-formed document","score":0.6047659516334534},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5951697826385498},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5889752507209778},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5530324578285217},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5486274361610413},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5224501490592957},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5210456252098083},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.5136601328849792},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4486510753631592},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.3064553141593933},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20093268156051636},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06886634230613708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343642950057983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7135394215583801},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6268117427825928},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.6047659516334534},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5951697826385498},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5889752507209778},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5530324578285217},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5486274361610413},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5224501490592957},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5210456252098083},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.5136601328849792},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4486510753631592},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3064553141593933},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20093268156051636},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06886634230613708},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1277741.1277877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.4758","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.4758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.qmul.ac.uk/~mounia/CV/Papers/sigir07bep.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1519066168","https://openalex.org/W1751758135","https://openalex.org/W1970889718","https://openalex.org/W2029177986","https://openalex.org/W2045117606","https://openalex.org/W2158387273","https://openalex.org/W2997501009","https://openalex.org/W4294621867"],"related_works":["https://openalex.org/W2051616516","https://openalex.org/W2374990542","https://openalex.org/W2584791291","https://openalex.org/W1639149850","https://openalex.org/W2011024487","https://openalex.org/W2351590241","https://openalex.org/W2353138694","https://openalex.org/W2605223516","https://openalex.org/W2352672621","https://openalex.org/W2027019938"],"abstract_inverted_index":{"In":[0],"structured":[1],"information":[2,50],"retrieval,":[3],"the":[4,16,22,29,40,42,48,52,56,64,74,84,91,94,99,105,117],"aim":[5],"is":[6],"to":[7,11,18,21,38,46],"exploit":[8],"document":[9],"structure":[10],"retrieve":[12],"relevant":[13,23,49,61,107,110,120,132,144],"components,":[14],"allowing":[15],"user":[17,41],"go":[19],"straight":[20],"material.":[24],"This":[25],"paper":[26],"looks":[27],"at":[28],"so-called":[30],"best":[31,43,85,100],"entry":[32,86,101],"points":[33,102],"(BEPs),":[34],"which":[35],"are":[36,73,79],"intended":[37],"give":[39],"starting":[44],"point":[45,87],"access":[47],"in":[51,63,109,127,140],"document.":[53,95],"We":[54],"examine":[55],"relationship":[57],"between":[58,116],"BEPs":[59,126,136,139],"and":[60,119,134],"components":[62],"INEX":[65],"2006":[66],"ad":[67],"hoc":[68],"assessments.":[69],"Our":[70],"main":[71],"findings":[72],"following:":[75],"First,":[76],"although":[77],"documents":[78],"short,":[80],"assessors":[81],"often":[82],"choose":[83],"some":[88],"distance":[89],"from":[90],"start":[92],"of":[93,98],"Second,":[96],"many":[97],"coincide":[103],"with":[104,129,142],"first":[106],"character":[108],"documents,":[111],"showing":[112],"a":[113,130],"strong":[114],"relation":[115],"BEP":[118],"text.":[121],"Third,":[122],"we":[123],"find":[124],"browsing":[125],"articles":[128,141],"single":[131],"passages,":[133],"container":[135],"or":[137],"context":[138],"more":[143],"passages.":[145]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
