{"id":"https://openalex.org/W2094228319","doi":"https://doi.org/10.1145/1277741.1277941","title":"An effective method for finding best entry points in semi-structured documents","display_name":"An effective method for finding best entry points in semi-structured documents","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2094228319","doi":"https://doi.org/10.1145/1277741.1277941","mag":"2094228319"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277941","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":"preprint","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/A5049830038","display_name":"Eugen Popovici","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Eugen Popovici","raw_affiliation_strings":["University of South-Brittany, Vannes, France"],"affiliations":[{"raw_affiliation_string":"University of South-Brittany, Vannes, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037347942","display_name":"Pierre-Fran\u00e7ois Marteau","orcid":"https://orcid.org/0000-0002-3963-8795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre-Fran\u00e7ois Marteau","raw_affiliation_strings":["University of South-Brittany, Vannes, France"],"affiliations":[{"raw_affiliation_string":"University of South-Brittany, Vannes, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113711969","display_name":"Gildas M\u00e9nier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gildas M\u00e9nier","raw_affiliation_strings":["University of South-Brittany, Vannes, France"],"affiliations":[{"raw_affiliation_string":"University of South-Brittany, Vannes, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049830038"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1271052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9955000281333923,"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":0.9955000281333923,"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/T11106","display_name":"Data Management and Algorithms","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9940000176429749,"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":0.8374033570289612},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7444972991943359},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7430332899093628},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.7373813390731812},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.6736817955970764},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5261905789375305},{"id":"https://openalex.org/keywords/well-formed-document","display_name":"Well-formed document","score":0.4799956977367401},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.4272924065589905},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3516732454299927},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.29159337282180786},{"id":"https://openalex.org/keywords/xml-signature","display_name":"XML Signature","score":0.18613028526306152},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05430406332015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374033570289612},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7444972991943359},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7430332899093628},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.7373813390731812},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6736817955970764},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5261905789375305},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.4799956977367401},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.4272924065589905},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3516732454299927},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.29159337282180786},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.18613028526306152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05430406332015991},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277941","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:10.1.1.109.765","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-valoria.univ-ubs.fr/Eugen.Popovici/pdf/SIGIR07/popoviciSIGIR07BEPv003.5wA.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00492979v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00492979","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annual ACM Conference on Research and Development in Information Retrieval, Jul 2007, Amsterdam, Netherlands. pp.851 - 852, &#x27E8;10.1145/1277741.1277941&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1596660743","https://openalex.org/W1970889718","https://openalex.org/W1979133853","https://openalex.org/W2029177986","https://openalex.org/W2045117606","https://openalex.org/W2173127389","https://openalex.org/W2997501009","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2011024487","https://openalex.org/W2351083423","https://openalex.org/W2024164996","https://openalex.org/W2058941326","https://openalex.org/W1972245780","https://openalex.org/W2112528798","https://openalex.org/W2347497444","https://openalex.org/W2146760738","https://openalex.org/W2352672621","https://openalex.org/W2605223516"],"abstract_inverted_index":{"Focused":[0],"structured":[1],"document":[2,26],"retrieval":[3],"employs":[4],"the":[5,47,55,61,64],"concept":[6],"of":[7,49,63],"best":[8],"entry":[9],"point":[10],"(BEP),":[11],"which":[12,20],"is":[13],"intended":[14],"to":[15,24],"provide":[16],"optimal":[17],"starting-point":[18],"from":[19],"users":[21],"can":[22],"browse":[23],"relevant":[25],"components":[27],"[4].":[28],"In":[29],"this":[30],"paper":[31],"we":[32],"describe":[33],"and":[34],"evaluate":[35],"a":[36],"method":[37],"for":[38],"finding":[39],"BEPs":[40],"in":[41],"XML":[42,57],"documents.":[43],"Experiments":[44],"conducted":[45],"within":[46],"framework":[48],"INEX":[50],"2006":[51],"evaluation":[52],"campaign":[53],"on":[54],"Wikipedia":[56],"collection":[58],"[2]":[59],"shown":[60],"effectiveness":[62],"proposed":[65],"approach.":[66]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
