{"corpus_id":52263012,"paper_sha":"6a16c48f5e0ec94fa20c9b5dffbe4cd0d0703738","doi":"10.1109/TVCG.2019.2895642","arxiv_id":null,"pmid":30735999,"pmcid":null,"mag_id":2911345638,"dblp_id":"journals/tvcg/MahmoodM20","acl_id":null,"title":"Taxonomizer: Interactive Construction of Fully Labeled Hierarchical Groupings from Attributes of Multivariate Data","year":2020,"publication_date":"2020-09-01","venue":"IEEE Transactions on Visualization and Computer Graphics","journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","pages":"2875-2890","volume":"26"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article","Research Support, U.S. Gov't, Non-P.H.S.","Research Support, Non-U.S. Gov't"],"s2_fields_of_study":["Biology","Medicine","Computer Science"],"reference_count":53,"citation_count":7,"influential_citation_count":0,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Organizing multivariate data spaces by their dimensions or attributes can be a rather difficult task. Most of the work in this area focuses on the statistical aspects such as correlation clustering, dimension reduction, and the like. These methods typically produce hierarchies in which the leaf nodes are labeled by the attribute names while the inner nodes are often represented by just a statistical measure and criterion, such as a threshold. This makes them difficult to understand for mainstream users. Taxonomies in science, biology, engineering, etc. on the other hand, are easy to comprehend since they provide meaningful labels at the inner nodes as well. Labeling inner nodes of taxonomies automatically requires the identification of hypernyms. Our proposed framework, called Taxonomizer, takes a visual analytics approach to meet this challenge. It appeals to the wisdom of humans to liaise with state of the art data analytics, neural word embeddings, and lexical databases. It consists of a set of visual tools that starts out with an automatically computed hierarchy where the leaf nodes are the original data attributes, and it then allows users to sculpt high-quality taxonomies for any multivariate dataset.","claims":[{"public_id":"cl_f5cbc9ef10596fa9bc99f3aa56d30c5b","status":"active","text":"Inner-node labeling is supported by identifying hypernyms with a combination of human input, data analytics, neural word embeddings, and lexical databases.","confidence":0.9,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_f5cbc9ef10596fa9bc99f3aa56d30c5b"},{"public_id":"cl_4e9db410821611ec7aac23d01f4d64b0","status":"active","text":"Taxonomizer provides an interactive visual analytics framework for sculpting high-quality taxonomies from any multivariate dataset.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_4e9db410821611ec7aac23d01f4d64b0"},{"public_id":"cl_95380589ed342a9caf432edcd6128f38","status":"active","text":"The approach is intended to produce fully labeled hierarchical groupings that are easier to understand than hierarchies whose inner nodes are represented only by statistical measures or thresholds.","confidence":0.86,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_95380589ed342a9caf432edcd6128f38"},{"public_id":"cl_3e084029ca26e81ccd59837e922e5b32","status":"active","text":"The framework begins with an automatically computed hierarchy whose leaf nodes are the original data attributes.","confidence":0.92,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_3e084029ca26e81ccd59837e922e5b32"}],"concepts":[{"public_id":"co_0ed3d5ec2b92f2916cd31c75131d2360","status":"active","name":"statistical measures","description":"Quantitative criteria used to characterize hierarchy nodes in traditional clustering-based methods.","types":["measure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_0ed3d5ec2b92f2916cd31c75131d2360"},{"public_id":"co_1148511a2402b1c7687a506b3b72727b","status":"active","name":"human input","description":"User involvement in refining and labeling the hierarchy through interactive tools.","types":["interaction"],"aliases":["wisdom of humans"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1148511a2402b1c7687a506b3b72727b"},{"public_id":"co_15bf379ab9aa6ff471bf8dcda517264a","status":"active","name":"multivariate dataset","description":"A dataset whose records are described by multiple attributes or dimensions.","types":["dataset"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_15bf379ab9aa6ff471bf8dcda517264a"},{"public_id":"co_318c13d8cd5f2786132036f36e876b5e","status":"active","name":"automatically computed hierarchy","description":"A hierarchy generated by an algorithm before user refinement, used as the starting structure in the framework.","types":["hierarchy"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_318c13d8cd5f2786132036f36e876b5e"},{"public_id":"co_4d22558f00db4d6d646ef0e96d2e6ef9","status":"active","name":"lexical databases","description":"Structured resources of words and their semantic relations used to support term lookup.","types":["resource"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4d22558f00db4d6d646ef0e96d2e6ef9"},{"public_id":"co_4fbd90af2910523e71e3619d6927c60d","status":"active","name":"Taxonomizer","description":"A visual analytics framework for interactively constructing labeled taxonomies from multivariate data attributes.","types":["framework","method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4fbd90af2910523e71e3619d6927c60d"},{"public_id":"co_62a9d71f20ef6691cfba545c4c1a1c8a","status":"active","name":"leaf nodes","description":"The terminal nodes of a hierarchy that correspond to the original attributes in the starting tree.","types":["hierarchy component"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_62a9d71f20ef6691cfba545c4c1a1c8a"},{"public_id":"co_7e431ae48b1c8f9b677833b3b7196c1a","status":"active","name":"neural word embeddings","description":"Vector representations of words used to support semantic matching or term identification.","types":["representation","method"],"aliases":["word embeddings"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7e431ae48b1c8f9b677833b3b7196c1a"},{"public_id":"co_af999bdaa5bf55437baefdad98010a03","status":"active","name":"visual analytics","description":"An approach that combines interactive visualization with computational analysis to support data understanding and decision making.","types":["approach"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_af999bdaa5bf55437baefdad98010a03"},{"public_id":"co_df7a463704be24c503d4a4c5f18d2b16","status":"active","name":"data attributes","description":"The individual dimensions or variables used to describe a multivariate dataset.","types":["feature","variable"],"aliases":["attributes"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_df7a463704be24c503d4a4c5f18d2b16"},{"public_id":"co_e5308a32d2db75246ea9e979d70a6855","status":"active","name":"taxonomy","description":"A hierarchical organization of items in which inner nodes and leaves are assigned meaningful labels.","types":["hierarchical structure"],"aliases":["taxonomies"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e5308a32d2db75246ea9e979d70a6855"},{"public_id":"co_ed2e9e3c9d3fd068764c845588464b5a","status":"active","name":"fully labeled hierarchical groupings","description":"Hierarchical groupings in which both leaf and inner nodes carry descriptive labels.","types":["hierarchical structure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ed2e9e3c9d3fd068764c845588464b5a"},{"public_id":"co_ef886886b05d424413eb74fb5b36370b","status":"active","name":"hypernyms","description":"More general terms used to label inner nodes in a taxonomy.","types":["linguistic concept"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ef886886b05d424413eb74fb5b36370b"},{"public_id":"co_fbeb07f24c443883f3bf40012d2ba580","status":"active","name":"thresholds","description":"Criterion values used to define splits or boundaries in hierarchical constructions.","types":["parameter"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_fbeb07f24c443883f3bf40012d2ba580"}],"external_ids":{"DOI":"10.1109/TVCG.2019.2895642","ArXiv":null,"PubMed":30735999,"PubMedCentral":null,"MAG":2911345638,"DBLP":"journals/tvcg/MahmoodM20","ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/52263012","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":632299,"paper_uid":"a054e716-d3c7-437e-96ad-07973c608cb3","canonical_identity":{"paper_id":632299,"paper_uid":"a054e716-d3c7-437e-96ad-07973c608cb3","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/52263012"}