{"id":"https://openalex.org/W1965693916","doi":"https://doi.org/10.1145/1390334.1390534","title":"XML-aided phrase indexing for hypertext documents","display_name":"XML-aided phrase indexing for hypertext documents","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W1965693916","doi":"https://doi.org/10.1145/1390334.1390534","mag":"1965693916"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","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/A5051929441","display_name":"Miro Lehtonen","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Miro Lehtonen","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["University of Caen, Caen, France","[University of Caen, Caen, France]"],"affiliations":[{"raw_affiliation_string":"University of Caen, Caen, France","institution_ids":["https://openalex.org/I98702875"]},{"raw_affiliation_string":"[University of Caen, Caen, France]","institution_ids":["https://openalex.org/I98702875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051929441"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":0.8747,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83444529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9948999881744385,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9948999881744385,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9922999739646912,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9886000156402588,"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":0.8710359334945679},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7277894020080566},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.704663872718811},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6828292608261108},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6770066022872925},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.5699172019958496},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5643097162246704},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.5551191568374634},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.4765908420085907},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4688735008239746},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.4681335389614105},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4133968949317932},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24954333901405334},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07214376330375671}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710359334945679},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7277894020080566},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.704663872718811},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6828292608261108},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6770066022872925},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.5699172019958496},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5643097162246704},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.5551191568374634},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.4765908420085907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4688735008239746},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.4681335389614105},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4133968949317932},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24954333901405334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07214376330375671},{"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:10.1145/1390334.1390534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.2208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.2208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.helsinki.fi/u/doucet/papers/sigir08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1529075208","https://openalex.org/W1593045043","https://openalex.org/W1598964704","https://openalex.org/W1981137801","https://openalex.org/W2126016680","https://openalex.org/W2282417977","https://openalex.org/W2995645267"],"related_works":["https://openalex.org/W2047342127","https://openalex.org/W2276215951","https://openalex.org/W2121785123","https://openalex.org/W2024164996","https://openalex.org/W2115478919","https://openalex.org/W2093637352","https://openalex.org/W2137809776","https://openalex.org/W56340752","https://openalex.org/W1509918510","https://openalex.org/W298511494"],"abstract_inverted_index":{"We":[0],"combine":[1],"techniques":[2],"of":[3,12,25,51],"XML":[4,23],"Mining":[5,8],"and":[6],"Text":[7],"for":[9],"the":[10,17,22,26,40,49,52,62,67],"benefit":[11],"Information":[13],"Retrieval.":[14],"By":[15],"manipulating":[16],"word":[18],"sequence":[19],"according":[20],"to":[21,39],"structure":[24],"marked-up":[27],"text,":[28],"we":[29],"strengthen":[30],"phrase":[31],"boundaries":[32],"so":[33],"that":[34,42],"they":[35],"are":[36],"more":[37],"obvious":[38],"algorithms":[41],"extract":[43],"multiword":[44],"sequences":[45],"from":[46],"text.":[47],"Consequently,":[48],"quality":[50],"indexed":[53],"phrases":[54],"improves,":[55],"which":[56],"has":[57],"a":[58],"positive":[59],"effect":[60],"on":[61],"average":[63],"precision":[64],"measured":[65],"by":[66],"INEX":[68],"2007":[69],"standards.":[70]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}