{"id":"https://openalex.org/W1965956170","doi":"https://doi.org/10.1145/1099554.1099666","title":"Inferring document similarity from hyperlinks","display_name":"Inferring document similarity from hyperlinks","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W1965956170","doi":"https://doi.org/10.1145/1099554.1099666","mag":"1965956170"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099666","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 ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Samy Bengio","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.2323,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.79690794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/hyperlink","display_name":"Hyperlink","score":0.933462381362915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8152515888214111},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.785228967666626},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6679237484931946},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4946386516094208},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4742785394191742},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4590628743171692},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3868267834186554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2779104709625244},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2604992985725403},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.19308006763458252},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07805439829826355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07593345642089844}],"concepts":[{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.933462381362915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152515888214111},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.785228967666626},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6679237484931946},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4946386516094208},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4742785394191742},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4590628743171692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3868267834186554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2779104709625244},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2604992985725403},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.19308006763458252},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07805439829826355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07593345642089844},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1145/1099554.1099666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099666","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 ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.376.5109","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.376.5109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2005/grangier-rr-05-21.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.1920","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.1920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.pascal-network.org/archive/00001098/01/grangier_2005_cikm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.390","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bengio.abracadoudou.com/cv/publications/pdf/rr05-21.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.7778","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.7778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~grangier/pub/papers/2005/grangier-2005-cikm.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:83191","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83219","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:83191","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1488394244","https://openalex.org/W1554663460","https://openalex.org/W1660390307","https://openalex.org/W1854214752","https://openalex.org/W1880262756","https://openalex.org/W1978381081","https://openalex.org/W2014134732","https://openalex.org/W2066636486","https://openalex.org/W2096041903","https://openalex.org/W2098162425","https://openalex.org/W2108346334","https://openalex.org/W2117154949","https://openalex.org/W2118393783","https://openalex.org/W2128390192","https://openalex.org/W2134731454","https://openalex.org/W2147152072","https://openalex.org/W2914484425","https://openalex.org/W4205686602","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W2898077673","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W3002840018"],"abstract_inverted_index":{"Assessing":[0],"semantic":[1],"similarity":[2,26],"between":[3],"text":[4,36],"documents":[5,44,73],"is":[6],"a":[7,25,54,61,68],"crucial":[8],"aspect":[9],"in":[10],"Information":[11],"Retrieval":[12],"systems.":[13],"In":[14],"this":[15,87],"work,":[16],"we":[17,52],"propose":[18],"to":[19,23,33,59,71,75],"use":[20,53],"hyperlink":[21],"information":[22],"derive":[24],"measure":[27],"that":[28,66,86],"can":[29],"then":[30],"be":[31],"applied":[32],"compare":[34],"any":[35],"documents,":[37,51],"with":[38,57,91],"or":[39],"without":[40],"hyperlinks.":[41],"As":[42],"linked":[43,72],"are":[45],"generally":[46],"semantically":[47],"closer":[48],"than":[49,74],"unlinked":[50,76],"training":[55],"corpus":[56],"hyperlinks":[58],"infer":[60],"function":[62,88],"a,b":[63],"\u2192":[64],"sim(a,b)":[65],"assigns":[67],"higher":[69],"value":[70],"ones.":[77],"Two":[78],"sets":[79],"of":[80],"experiments":[81],"on":[82,94],"different":[83],"corpora":[84],"show":[85],"compares":[89],"favorably":[90],"OKAPI":[92],"matching":[93],"document":[95],"retrieval":[96],"tasks.":[97]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
