{"id":"https://openalex.org/W3046775778","doi":"https://doi.org/10.1145/3400903.3400926","title":"An Algebraic Approach for High-level Text Analytics","display_name":"An Algebraic Approach for High-level Text Analytics","publication_year":2020,"publication_date":"2020-07-07","ids":{"openalex":"https://openalex.org/W3046775778","doi":"https://doi.org/10.1145/3400903.3400926","mag":"3046775778"},"language":"en","primary_location":{"id":"doi:10.1145/3400903.3400926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3400903.3400926","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3400903.3400926","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"32nd International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3400903.3400926","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005837780","display_name":"Xiuwen Zheng","orcid":"https://orcid.org/0000-0002-1390-0708"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiuwen Zheng","raw_affiliation_strings":["San Diego Supercomputer Center at University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center at University of California San Diego","institution_ids":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057846313","display_name":"Amarnath Gupta","orcid":"https://orcid.org/0000-0003-0897-120X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amarnath Gupta","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0873751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8142796754837036},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.605135440826416},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5967776775360107},{"id":"https://openalex.org/keywords/relational-algebra","display_name":"Relational algebra","score":0.5834810137748718},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5771088004112244},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.576693058013916},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.560777485370636},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.44331514835357666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3549787998199463},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33871084451675415},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2764708995819092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2569115459918976},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.256804883480072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08499020338058472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142796754837036},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.605135440826416},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5967776775360107},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.5834810137748718},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5771088004112244},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.576693058013916},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.560777485370636},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.44331514835357666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3549787998199463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33871084451675415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2764708995819092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2569115459918976},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.256804883480072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08499020338058472},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3400903.3400926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3400903.3400926","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3400903.3400926","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"32nd International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3400903.3400926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3400903.3400926","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3400903.3400926","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"32nd International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4654633617","display_name":"III:Small: Towards Cross-Model Query Optimizations for Multi-model Heterogeneous Data Analytics","funder_award_id":"1909875","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046775778.pdf","grobid_xml":"https://content.openalex.org/works/W3046775778.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W616288317","https://openalex.org/W2775406941","https://openalex.org/W3002028770"],"related_works":["https://openalex.org/W2085988990","https://openalex.org/W2056340443","https://openalex.org/W2143485006","https://openalex.org/W2005835473","https://openalex.org/W3174970460","https://openalex.org/W2376710457","https://openalex.org/W2950556518","https://openalex.org/W4383617113","https://openalex.org/W1979093255","https://openalex.org/W1974946854"],"abstract_inverted_index":{"Text":[0],"analytical":[1],"tasks":[2],"like":[3],"word":[4],"embedding,":[5],"phrase":[6],"mining":[7],"and":[8,40,47,63],"topic":[9],"modeling,":[10],"are":[11],"placing":[12],"increasing":[13],"demands":[14],"as":[15,17],"well":[16],"challenges":[18],"to":[19],"existing":[20],"database":[21],"management":[22],"systems.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"provide":[28],"a":[29],"novel":[30],"algebraic":[31],"approach":[32],"based":[33],"on":[34],"associative":[35],"arrays.":[36],"Our":[37],"data":[38,57],"model":[39],"algebra":[41],"can":[42],"bring":[43],"together":[44],"relational":[45,62],"operators":[46],"text":[48,72],"operators,":[49],"which":[50],"enables":[51],"interesting":[52],"optimization":[53],"opportunities":[54],"for":[55],"hybrid":[56],"sources":[58],"that":[59],"have":[60],"both":[61],"textual":[64],"data.":[65],"We":[66],"demonstrate":[67],"its":[68],"expressive":[69],"power":[70],"in":[71],"analytics":[73],"using":[74],"several":[75],"real-world":[76],"tasks.":[77]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}