{"id":"https://openalex.org/W2069662697","doi":"https://doi.org/10.1145/2428736.2428784","title":"Test collection recycling for semantic text similarity","display_name":"Test collection recycling for semantic text similarity","publication_year":2012,"publication_date":"2012-12-03","ids":{"openalex":"https://openalex.org/W2069662697","doi":"https://doi.org/10.1145/2428736.2428784","mag":"2069662697"},"language":"en","primary_location":{"id":"doi:10.1145/2428736.2428784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2428736.2428784","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 International Conference on Information Integration and Web-based Applications & Services","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/A5061601620","display_name":"Faisal Rahutomo","orcid":"https://orcid.org/0000-0002-1312-1659"},"institutions":[{"id":"https://openalex.org/I102893293","display_name":"State University of Malang","ror":"https://ror.org/00ypgyy34","country_code":"ID","type":"education","lineage":["https://openalex.org/I102893293"]},{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["ID","JP"],"is_corresponding":false,"raw_author_name":"Faisal Rahutomo","raw_affiliation_strings":["State Polytechnics of Malang, Malang, Indonesia and Kumamoto University, Kumamoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Polytechnics of Malang, Malang, Indonesia and Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I102893293","https://openalex.org/I96036126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049350075","display_name":"Teruaki Kitasuka","orcid":null},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Teruaki Kitasuka","raw_affiliation_strings":["Kumamoto University, Kumamoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010583900","display_name":"Masayoshi Aritsugi","orcid":"https://orcid.org/0000-0003-0861-849X"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayoshi Aritsugi","raw_affiliation_strings":["Kumamoto University, Kumamoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.041,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.75928538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/jaccard-index","display_name":"Jaccard index","score":0.8723037242889404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7996032238006592},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7364847660064697},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.7353570461273193},{"id":"https://openalex.org/keywords/retrievability","display_name":"Retrievability","score":0.7124778032302856},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6465439200401306},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6341874003410339},{"id":"https://openalex.org/keywords/explicit-semantic-analysis","display_name":"Explicit semantic analysis","score":0.574769139289856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5510500073432922},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5189542770385742},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5093129873275757},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.4877391755580902},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.476538747549057},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45690691471099854},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4268856644630432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4201662242412567},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2463797926902771},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.15798816084861755},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.11598557233810425},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10658630728721619},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.10502538084983826}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8723037242889404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996032238006592},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7364847660064697},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.7353570461273193},{"id":"https://openalex.org/C191072391","wikidata":"https://www.wikidata.org/wiki/Q17043235","display_name":"Retrievability","level":3,"score":0.7124778032302856},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6465439200401306},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6341874003410339},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.574769139289856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5510500073432922},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5189542770385742},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5093129873275757},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.4877391755580902},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.476538747549057},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45690691471099854},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4268856644630432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4201662242412567},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2463797926902771},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.15798816084861755},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.11598557233810425},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10658630728721619},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.10502538084983826},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2428736.2428784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2428736.2428784","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 International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W145425800","https://openalex.org/W174630521","https://openalex.org/W1566018662","https://openalex.org/W1607035479","https://openalex.org/W1610356397","https://openalex.org/W1980318031","https://openalex.org/W2045929671","https://openalex.org/W2101105183","https://openalex.org/W2120779048","https://openalex.org/W2121184547","https://openalex.org/W2127453322","https://openalex.org/W2133436118","https://openalex.org/W2145819623","https://openalex.org/W2164290393","https://openalex.org/W2251109811","https://openalex.org/W6691695795"],"related_works":["https://openalex.org/W2890241594","https://openalex.org/W1976495436","https://openalex.org/W2386038056","https://openalex.org/W1977854250","https://openalex.org/W4322096533","https://openalex.org/W3016822073","https://openalex.org/W2104074092","https://openalex.org/W2403224004","https://openalex.org/W1973958150","https://openalex.org/W2069662697"],"abstract_inverted_index":{"Semantic":[0],"text":[1,18,28],"similarity":[2],"(STS)":[3],"uses":[4],"specific":[5],"test":[6,14,39,49,64,77,98,103,125],"collections":[7,15,50,126],"as":[8,115],"its":[9],"performance":[10],"evaluation":[11,116],"measurement.":[12],"The":[13,30],"consist":[16],"of":[17,62,96],"pairs":[19,55],"with":[20,35,100],"the":[21,44,59,89,123,136],"same":[22],"meaning":[23],"even":[24],"though":[25],"in":[26],"different":[27],"form.":[29],"existence":[31],"is":[32],"scarce":[33],"compared":[34],"information":[36],"retrieval":[37],"(IR)":[38],"collections.":[40,65],"This":[41],"paper":[42],"investigates":[43],"possibility":[45],"to":[46],"reuse":[47],"IR":[48,63],"for":[51],"STS":[52],"tasks.":[53],"Text":[54],"are":[56,80],"derived":[57],"from":[58],"relevant":[60],"pair":[61],"Latent":[66],"semantic":[67,72],"analysis":[68,73],"(LSA)":[69],"and":[70,109,131],"explicit":[71],"(ESA)":[74],"evaluate":[75],"Glasgow's":[76],"collections,":[78,104],"which":[79],"provided":[81],"by":[82],"ACM":[83],"SIGIR":[84],"community.":[85],"Jaccard":[86,129],"index":[87,130],"measures":[88,94],"lexical":[90],"similarity.":[91],"Recall":[92],"metric":[93],"retrievability":[95],"recycling":[97],"collection":[99],"two":[101,137],"existing":[102],"Microsoft":[105,110],"research":[106,111],"paraphrase":[107],"corpus":[108],"video":[112],"description":[113],"corpus,":[114],"baselines.":[117,138],"Evaluation":[118],"yields":[119],"a":[120],"promising":[121],"outcome;":[122],"evaluated":[124],"have":[127],"low":[128],"their":[132],"recall":[133],"values":[134],"between":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}