{"id":"https://openalex.org/W2143101780","doi":"https://doi.org/10.1145/1148170.1148334","title":"Measuring similarity of semi-structured documents with context weights","display_name":"Measuring similarity of semi-structured documents with context weights","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2143101780","doi":"https://doi.org/10.1145/1148170.1148334","mag":"2143101780"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5086292931","display_name":"Christopher C. Yang","orcid":"https://orcid.org/0000-0001-5463-6926"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Christopher C. Yang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367554","display_name":"Nan Liu","orcid":"https://orcid.org/0000-0003-3610-4883"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086292931"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.807,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87523499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983000159263611,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9983000159263611,"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":0.6821524500846863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.642471194267273},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6180001497268677},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6171578168869019},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44216105341911316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34105658531188965},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0928066074848175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821524500846863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.642471194267273},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6180001497268677},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6171578168869019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44216105341911316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34105658531188965},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0928066074848175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1564068099","https://openalex.org/W1988110209","https://openalex.org/W2023182948"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2076713575","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"study":[4],"similarity":[5],"measures":[6],"for":[7],"text-centric":[8],"XML":[9,46],"documents":[10],"based":[11,27],"on":[12,28],"an":[13],"extended":[14],"vector":[15],"space":[16],"model,":[17],"which":[18,41],"considers":[19],"both":[20],"document":[21],"content":[22],"and":[23],"structure.":[24],"Experimental":[25],"results":[26],"a":[29],"benchmark":[30],"showed":[31],"superior":[32],"performance":[33],"of":[34,45],"the":[35,39],"proposed":[36],"measure":[37],"over":[38],"baseline":[40],"ignores":[42],"structural":[43],"knowledge":[44],"documents.":[47]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}