{"id":"https://openalex.org/W2951464182","doi":"https://doi.org/10.1109/icde.2019.00200","title":"Domain-Independent Automated Processing of Free-Form Text Data in Telecom","display_name":"Domain-Independent Automated Processing of Free-Form Text Data in Telecom","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2951464182","doi":"https://doi.org/10.1109/icde.2019.00200","mag":"2951464182"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2019.00200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2019.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 35th International Conference on Data Engineering (ICDE)","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/A5030152944","display_name":"Rajarshi Bhowmik","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajarshi Bhowmik","raw_affiliation_strings":["Department of Computer Science, Rutgers University, Piscataway, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, Piscataway, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086691488","display_name":"Akyamac Ahmet","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmet Akyamac","raw_affiliation_strings":["Bell Labs, Nokia, New Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bell Labs, Nokia, New Jersey, USA","institution_ids":["https://openalex.org/I72090969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.328,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59082252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1841","last_page":"1849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9889000058174133,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8304697275161743},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6801842451095581},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5688862204551697},{"id":"https://openalex.org/keywords/jargon","display_name":"Jargon","score":0.5538519620895386},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5411983132362366},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5315014719963074},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5258327722549438},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5127114057540894},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.507632851600647},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.48443177342414856},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.45570075511932373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42743125557899475},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4270518124103546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621438145637512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33447861671447754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33062756061553955},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3068472146987915},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09405019879341125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304697275161743},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6801842451095581},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5688862204551697},{"id":"https://openalex.org/C2777611551","wikidata":"https://www.wikidata.org/wiki/Q17951","display_name":"Jargon","level":2,"score":0.5538519620895386},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5411983132362366},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5315014719963074},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5258327722549438},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5127114057540894},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.507632851600647},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.48443177342414856},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.45570075511932373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42743125557899475},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4270518124103546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621438145637512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33447861671447754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33062756061553955},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3068472146987915},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09405019879341125},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2019.00200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2019.00200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 35th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"mag:3089964816","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902238151381028","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W148350307","https://openalex.org/W1525595230","https://openalex.org/W1606631988","https://openalex.org/W1832693441","https://openalex.org/W1880262756","https://openalex.org/W2012833704","https://openalex.org/W2036114820","https://openalex.org/W2064418625","https://openalex.org/W2097847889","https://openalex.org/W2133286915","https://openalex.org/W2145766604","https://openalex.org/W2163659824","https://openalex.org/W2167329753","https://openalex.org/W2170240176","https://openalex.org/W2265846598","https://openalex.org/W4230940751","https://openalex.org/W4253735685","https://openalex.org/W6605939760","https://openalex.org/W6631501603","https://openalex.org/W6639619044","https://openalex.org/W6683944584","https://openalex.org/W6685053522","https://openalex.org/W6693505360"],"related_works":["https://openalex.org/W3040422808","https://openalex.org/W4317528635","https://openalex.org/W2499956125","https://openalex.org/W3210470316","https://openalex.org/W4389578080","https://openalex.org/W2600483492","https://openalex.org/W2339284686","https://openalex.org/W4385795891","https://openalex.org/W2602957669","https://openalex.org/W3130974824"],"abstract_inverted_index":{"Free-form,":[0],"unstructured":[1],"and":[2,17,34,37,47,54,96,128,143,156],"semi-structured":[3],"textual":[4,25,75,101],"data":[5,26,102],"has":[6],"become":[7],"increasingly":[8],"more":[9],"prevalent":[10],"in":[11,103],"the":[12,50,63,88,94,125],"telecommunications":[13],"industry,":[14],"with":[15,169],"service":[16],"equipment":[18],"providers":[19],"alike.":[20],"Some":[21],"typical":[22],"examples":[23],"include":[24],"from":[27,130,138],"customer":[28,140],"care":[29,141],"tickets,":[30],"machine":[31],"logs,":[32,145],"alarm":[33],"alerting":[35],"systems,":[36],"diagnostics.":[38],"There":[39],"is":[40,78],"a":[41,79,111,117],"growing":[42],"business":[43],"need":[44,81],"to":[45,73,82,86,93,159],"rapidly":[46],"automatically":[48,123],"understand":[49],"underlying":[51],"key":[52,126],"topics":[53,127],"categories":[55,129],"of":[56,60,66,68,100],"this":[57,104,107],"bulk":[58],"collection":[59],"text.":[61],"With":[62],"present":[64],"mode":[65],"operation":[67],"relying":[69],"on":[70],"domain":[71,167],"experts":[72,168],"analyze":[74],"data,":[76],"there":[77],"clear":[80],"apply":[83],"text":[84,119,132,153],"analytics":[85],"automate":[87],"process.":[89],"Difficulties":[90],"arise":[91],"due":[92],"jargon-filled":[95],"fragmented,":[97],"incomplete":[98],"nature":[99],"field.":[105],"In":[106],"paper,":[108],"we":[109,146],"propose":[110],"domain-agnostic,":[112],"unsupervised":[113],"approach":[114,150],"that":[115,148,163],"deploys":[116],"multi-stage":[118],"processing":[120],"pipeline":[121],"for":[122],"discovering":[124],"free-form":[131],"documents.":[133],"Using":[134],"anonymized":[135],"datasets":[136],"retrieved":[137],"actual":[139],"tickets":[142],"system":[144,171],"show":[147],"our":[149],"outperforms":[151],"traditional":[152],"mining":[154],"approaches,":[155],"performs":[157],"comparably":[158],"manual":[160],"categorization":[161],"tasks":[162],"were":[164],"undertaken":[165],"by":[166],"full":[170],"knowledge.":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}