{"entities":{"Q2193277":{"pageid":2204020,"ns":120,"title":"Item:Q2193277","lastrevid":71516625,"modified":"2026-04-13T22:46:51Z","type":"item","id":"Q2193277","labels":{"en":{"language":"en","value":"A semantic relatedness preserved subset extraction method for language corpora based on pseudo-Boolean optimization"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 7239083"}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$8B1D2755-D251-4192-A614-600FD8239B54","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"32a952d303d7cca7f164f855886239dc78419438","datavalue":{"value":{"text":"A semantic relatedness preserved subset extraction method for language corpora based on pseudo-Boolean optimization","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q2193277$BCB3BE04-AAC0-4F68-847F-EA00BEE7F540","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"9a802946b70e74c056bf52941f71cb02b5121128","datavalue":{"value":"1461.68237","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$AD18BF96-1AE1-4910-8035-4C133645C419","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"5e4dba5489972ff4a5e0623c51d723f7d625f648","datavalue":{"value":{"entity-type":"item","numeric-id":2079865,"id":"Q2079865"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$C39A5EE8-3D40-4AF2-8CE6-7727D1F4C007","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"2a53da3bb8f9b457fe401035550005b10f31b0dd","datavalue":{"value":{"entity-type":"item","numeric-id":1756091,"id":"Q1756091"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$E1CE49F5-6BC9-46C3-8147-375451781D0D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"f69510ef1de2b19c41be429e5cfc4fc3363cdc8f","datavalue":{"value":{"entity-type":"item","numeric-id":199274,"id":"Q199274"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$BDFD926D-5B92-4B84-88C5-2C6A8561FEAA","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"af3113a0352dee5a4b3888d137e0f86bb0117ad4","datavalue":{"value":{"entity-type":"item","numeric-id":2193276,"id":"Q2193276"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$DDE29917-7200-41AA-861B-A937710A4DC9","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"f3c424cd94a60f9664f9fb69cc6027e75cc7ff3f","datavalue":{"value":{"entity-type":"item","numeric-id":123643,"id":"Q123643"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$0F066205-1E23-4C85-903C-8977AE9A3C74","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"40d6298d979cc5fe8f26a1cea0e2ec254982529e","datavalue":{"value":{"time":"+2020-08-25T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q2193277$67A37EF2-B10F-4115-BF72-A1C1DBF6B92D","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"813c66effbd11fc78af6bfdb693a57ff83f6593f","datavalue":{"value":"Text corpora in natural-language research contain billions of words and the size is growing, which has created the problem of extracting smaller subsets with a minimally changed semantics. Let \\(T=\\{t_1,\\dots,t_n\\}\\) be a set of tokens (e.g. words) in an annotated text corpus with real-valued unary and binary attributes and semantic relatedness relations \\(S^1\\in\\mathcal{R}^n\\), \\(S^2\\in\\mathcal{R}^{n\\times n}\\), \\(S^3\\in\\mathcal{R}^{n\\times n\\times n}\\); \\(X=\\{x_1,\\dots,x_n\\}\\in\\{0,1\\}^n\\) be Boolean variables to denote subsets from \\(T\\). The problem of semantics relatedness preservation in corpora subset extraction is finding an `optimal' (minimal) subset \\(X\\subset T\\) which maximizes \\(\\sum\\limits_{i=1}^ns_i^1{x_i}+\\sum\\limits_{i,j=1}^ns_{ij}^2x_ix_j+\\sum\\limits_{i,j,k = 1}^ns_{ijk}^3x_ix_jx_k\\) under constraints for attributes (here, one unary and one binary attribute constraint are considered). This NP-hard problem is transformed into the problem of finding the maximum flow in an equivalent graph and solved using the discrete Lagrangian iteration method.","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$B77F6B98-CA3C-4B00-B380-0341944DAE38","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"ae62b6ae8284bad4753b7ed23b6f2503aa5e4b9f","datavalue":{"value":"68T50","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$9C1E1105-697F-433F-818E-0F026A89AED3","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"35cb8465ca85ba26995d54be2905dc35556d665c","datavalue":{"value":"90C27","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$4431D6FF-915A-4F93-ADCE-614503242CB7","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"92a9d15088f81f36527d9f33746e913026497d3f","datavalue":{"value":"7239083","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$8687327B-0B5A-42B5-B327-E45263F2798E","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"33323838b521ba83f6928998aedf07667aed832c","datavalue":{"value":"semantic relatedness","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$2A225649-A3AE-4BE0-AF6E-82CF51D4026D","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"5e88db4f8521b6f338d68b873c82544f0e7a6588","datavalue":{"value":"subset extraction","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$C7BC2137-9AD9-440A-81C3-CD159AB1DE1F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"5eebaa70f7bba8bea6822a980d19a61f951721ac","datavalue":{"value":"language intelligence","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$6CFBB7E6-C0D5-4448-B171-8B0A182CDFF8","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"08c009e1da85687f7d248bf3d529bee2d7b4b712","datavalue":{"value":"pseudo-Boolean optimization","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$80312DB3-2CAC-430A-87F3-DF642F8EC2B5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"cc9e4ff538a91e8b58c3f75a647f1cc85ce9ff3f","datavalue":{"value":"discrete Lagrangian method","type":"string"},"datatype":"string"},"type":"statement","id":"Q2193277$63B2C679-F37A-4850-9B30-DF57F3476232","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"4e1df29911c330da2d8d89435a35b182dae9e523","datavalue":{"value":{"entity-type":"item","numeric-id":589408,"id":"Q589408"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$0A738892-172E-49A0-A729-D3954704B0B9","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$A6CD6AB5-4BF3-41DC-B9B3-E1220181ACCA","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"e8694ac2e90823bf12c01ed7dc35cf283b646ccb","datavalue":{"value":"https://doi.org/10.1016/j.tcs.2020.07.020","type":"string"},"datatype":"url"},"type":"statement","id":"Q2193277$D694967C-D778-42EB-9B5C-185769234FE4","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"554ee62aacfae62ab0b001be72cdbcceee661b02","datavalue":{"value":"W3044921385","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$EFB1C92A-320D-4808-91C4-08503B1D3AD4","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"ba97524c753fe1ce2025788804ba84c443e774fa","datavalue":{"value":{"entity-type":"item","numeric-id":260013,"id":"Q260013"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$2E4AEBBE-8FE9-44D0-83C0-D937174ACA43","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"f89c01b0d791f584818188a0960a68757726249e","datavalue":{"value":{"entity-type":"item","numeric-id":1069444,"id":"Q1069444"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$AB78BD80-9D64-4B0A-B093-A7C4F4B4F77E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d5d2ff8ca55c71a00eb97ded234e95c181b7889c","datavalue":{"value":{"entity-type":"item","numeric-id":5603745,"id":"Q5603745"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$319E47BA-B728-4085-A9D8-7051B9245EEB","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"d0d02d1ea3c025df6a57e4eb8432aceff8f23709","datavalue":{"value":{"entity-type":"item","numeric-id":1383842,"id":"Q1383842"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$E1991BAA-08D2-4AB8-9D24-0FA705AE051A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P223","hash":"822fba3bf07334d37364c3af9475128e4d956445","datavalue":{"value":{"entity-type":"item","numeric-id":4607913,"id":"Q4607913"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q2193277$5B898597-E64A-4680-A3F8-4F1E0AF93FCF","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"43ea07dc2442802c068eefdd70a2bec3a6447427","datavalue":{"value":"10.1016/J.TCS.2020.07.020","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q2193277$D310FA1F-62CC-438E-BAF7-733D3E7ACBF8","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"01a0b7b786fb669d7d4b3e5fa6811d308d10c303","datavalue":{"value":{"entity-type":"item","numeric-id":4802485,"id":"Q4802485"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"0e98185d6758db9d7f9194bae415da31324974f1","datavalue":{"value":{"amount":"+0.6877682209014893","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2193277$C0B344B6-48C7-45CD-A784-216C2B8D34B2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"f15ff5bd0309886959620d6d51747c8912ceecd6","datavalue":{"value":{"entity-type":"item","numeric-id":5193017,"id":"Q5193017"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"d4e837769ec3f7167584110957d909f8488d53d7","datavalue":{"value":{"amount":"+0.6711916327476501","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2193277$9394DE10-FF80-4F58-9110-F474B497F0E4","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"af354f04e1f18380a350d9c88e2cd61390950fd3","datavalue":{"value":{"entity-type":"item","numeric-id":2850347,"id":"Q2850347"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"7ee428827ab1eaf0783ab668eebcbf64750161f7","datavalue":{"value":{"amount":"+0.6630268096923828","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2193277$0876B40C-F2ED-4293-8698-60D29CCB5717","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"096602aa9e8538ebece26b0692ecd82cb1e1ff5a","datavalue":{"value":{"entity-type":"item","numeric-id":1025681,"id":"Q1025681"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"5be5edd4d458cf49911c5a0ddc1169d7939b0d6f","datavalue":{"value":{"amount":"+0.6624853014945984","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2193277$FEA57582-A44D-4A5C-822E-B24DAE8BE266","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"03f7a2efe887ad12b1fca84ef2bc092420973e29","datavalue":{"value":{"entity-type":"item","numeric-id":868131,"id":"Q868131"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"93940911c428fb1d45665f93d8462ae0f4a932bf","datavalue":{"value":{"amount":"+0.6562452912330627","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q2193277$9809F0AB-D5DE-4763-A94B-66C23DB43C3E","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"A semantic relatedness preserved subset extraction method for language corpora based on pseudo-Boolean optimization","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/A_semantic_relatedness_preserved_subset_extraction_method_for_language_corpora_based_on_pseudo-Boolean_optimization"}}}}}