{"id":"https://openalex.org/W3091809435","doi":"https://doi.org/10.1145/3383455.3422537","title":"Paying down metadata debt","display_name":"Paying down metadata debt","publication_year":2020,"publication_date":"2020-10-15","ids":{"openalex":"https://openalex.org/W3091809435","doi":"https://doi.org/10.1145/3383455.3422537","mag":"3091809435"},"language":"en","primary_location":{"id":"doi:10.1145/3383455.3422537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422537","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422537","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422537","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiahao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiahao Chen","raw_affiliation_strings":["J. P. Morgan AI Research","J.P. Morgan AI Research"],"affiliations":[{"raw_affiliation_string":"J. P. Morgan AI Research","institution_ids":[]},{"raw_affiliation_string":"J.P. Morgan AI Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057963205","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0002-1995-095X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["J. P. Morgan AI Research","J.P. Morgan AI Research"],"affiliations":[{"raw_affiliation_string":"J. P. Morgan AI Research","institution_ids":[]},{"raw_affiliation_string":"J.P. Morgan AI Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12181608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9965000152587891,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9961000084877014,"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/interpretability","display_name":"Interpretability","score":0.8878339529037476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990676164627075},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7598247528076172},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6031169295310974},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.508363664150238},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5048056840896606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4662168622016907},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.45852604508399963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3638259172439575},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3357599377632141},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1339997947216034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10290548205375671}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8878339529037476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990676164627075},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7598247528076172},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6031169295310974},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.508363664150238},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5048056840896606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4662168622016907},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.45852604508399963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3638259172439575},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3357599377632141},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1339997947216034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10290548205375671},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3383455.3422537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422537","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422537","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3383455.3422537","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3383455.3422537","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3383455.3422537","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3091809435.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W758034074","https://openalex.org/W1567491469","https://openalex.org/W1902027874","https://openalex.org/W1968843188","https://openalex.org/W1972326413","https://openalex.org/W1982114217","https://openalex.org/W2044988198","https://openalex.org/W2058078260","https://openalex.org/W2091359547","https://openalex.org/W2118550318","https://openalex.org/W2128521126","https://openalex.org/W2147152072","https://openalex.org/W2156719288","https://openalex.org/W2162451874","https://openalex.org/W2164616133","https://openalex.org/W2268674159","https://openalex.org/W2963260187","https://openalex.org/W2963848703"],"related_works":["https://openalex.org/W10234003","https://openalex.org/W269549","https://openalex.org/W10962570","https://openalex.org/W11104910","https://openalex.org/W9516802","https://openalex.org/W12769952","https://openalex.org/W13002482","https://openalex.org/W8432713","https://openalex.org/W9292421","https://openalex.org/W2824197"],"abstract_inverted_index":{"We":[0,20,53,77,105],"introduce":[1,54],"a":[2,55],"data":[3,14],"management":[4],"problem":[5],"called":[6],"metadata":[7],"debt,":[8],"to":[9,48,62,75,81,125],"identify":[10],"the":[11,123],"mapping":[12,24],"between":[13,66],"concepts":[15],"and":[16,41,51,68,71,101],"their":[17],"logical":[18],"representations.":[19],"describe":[21],"how":[22,80],"this":[23,83,109],"can":[25],"be":[26],"learned":[27],"using":[28],"semisupervised":[29,87],"topic":[30,84,110],"models":[31],"based":[32],"on":[33,116],"low-rank":[34],"matrix":[35],"factorizations":[36],"that":[37,59],"account":[38],"for":[39,86],"missing":[40,103],"noisy":[42],"labels,":[43,70,94,100],"coupled":[44],"with":[45],"sparsity":[46],"penalties":[47],"improve":[49],"localization":[50],"interpretability.":[52],"gauge":[56],"transformation":[57],"approach":[58],"allows":[60],"us":[61],"construct":[63],"explicit":[64],"associations":[65],"topics":[67],"concept":[69],"thus":[72],"assign":[73],"meaning":[74],"topics.":[76],"also":[78],"show":[79,106],"use":[82],"model":[85,111],"learning":[88],"tasks":[89],"like":[90],"extrapolating":[91],"from":[92,108,120],"known":[93],"evaluating":[95],"possible":[96],"errors":[97],"in":[98,112],"existing":[99],"predicting":[102,113],"features.":[104,129],"results":[107],"subject":[114],"tags":[115],"over":[117],"25,000":[118],"datasets":[119],"Kaggle.com,":[121],"demonstrating":[122],"ability":[124],"learn":[126],"semantically":[127],"meaningful":[128]},"counts_by_year":[],"updated_date":"2026-01-15T23:16:33.117629","created_date":"2020-10-15T00:00:00"}