{"id":"https://openalex.org/W3108996037","doi":"https://doi.org/10.23919/cnsm50824.2020.9269096","title":"Unsupervised Noise Detection in Unstructured data for Automatic Parsing","display_name":"Unsupervised Noise Detection in Unstructured data for Automatic Parsing","publication_year":2020,"publication_date":"2020-11-02","ids":{"openalex":"https://openalex.org/W3108996037","doi":"https://doi.org/10.23919/cnsm50824.2020.9269096","mag":"3108996037"},"language":"en","primary_location":{"id":"doi:10.23919/cnsm50824.2020.9269096","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm50824.2020.9269096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 16th International Conference on Network and Service Management (CNSM)","raw_type":"proceedings-article"},"type":"article","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/A5005203615","display_name":"Shubham Jain","orcid":"https://orcid.org/0000-0002-0913-3948"},"institutions":[{"id":"https://openalex.org/I151939572","display_name":"Athlone Institute of Technology","ror":"https://ror.org/02dyxwz31","country_code":"IE","type":"education","lineage":["https://openalex.org/I151939572"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Shubham Jain","raw_affiliation_strings":["Athlone Institute of Technology,Software Research Institute,Athlone,Ireland","Software Research Institute, Athlone Institute of Technology, Athlone, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athlone Institute of Technology,Software Research Institute,Athlone,Ireland","institution_ids":["https://openalex.org/I151939572"]},{"raw_affiliation_string":"Software Research Institute, Athlone Institute of Technology, Athlone, Ireland","institution_ids":["https://openalex.org/I151939572"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082979434","display_name":"Amy de Buitl\u00e9ir","orcid":"https://orcid.org/0000-0001-8359-0920"},"institutions":[{"id":"https://openalex.org/I151939572","display_name":"Athlone Institute of Technology","ror":"https://ror.org/02dyxwz31","country_code":"IE","type":"education","lineage":["https://openalex.org/I151939572"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Amy de Buitl\u00e9ir","raw_affiliation_strings":["Network Management Lab,Athlone,Ireland","Network Management Lab, Athlone, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Network Management Lab,Athlone,Ireland","institution_ids":["https://openalex.org/I151939572"]},{"raw_affiliation_string":"Network Management Lab, Athlone, Ireland","institution_ids":["https://openalex.org/I151939572"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070072452","display_name":"Enda Fallon","orcid":"https://orcid.org/0000-0002-8300-5813"},"institutions":[{"id":"https://openalex.org/I151939572","display_name":"Athlone Institute of Technology","ror":"https://ror.org/02dyxwz31","country_code":"IE","type":"education","lineage":["https://openalex.org/I151939572"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Enda Fallon","raw_affiliation_strings":["Athlone Institute of Technology,Software Research Institute,Athlone,Ireland","Software Research Institute, Athlone Institute of Technology, Athlone, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athlone Institute of Technology,Software Research Institute,Athlone,Ireland","institution_ids":["https://openalex.org/I151939572"]},{"raw_affiliation_string":"Software Research Institute, Athlone Institute of Technology, Athlone, Ireland","institution_ids":["https://openalex.org/I151939572"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6483,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73319934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9868000149726868,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9796000123023987,"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":0.8723145723342896},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8267776370048523},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7322757840156555},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.7124837040901184},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6514702439308167},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.622542679309845},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5925135016441345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5694565773010254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5264288187026978},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48806679248809814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3940773010253906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34716373682022095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723145723342896},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8267776370048523},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7322757840156555},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.7124837040901184},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6514702439308167},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.622542679309845},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5925135016441345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5694565773010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264288187026978},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48806679248809814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3940773010253906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34716373682022095},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/cnsm50824.2020.9269096","is_oa":false,"landing_page_url":"https://doi.org/10.23919/cnsm50824.2020.9269096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 16th International Conference on Network and Service Management (CNSM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W1647671624","https://openalex.org/W1661413208","https://openalex.org/W1974648336","https://openalex.org/W2012833704","https://openalex.org/W2034190452","https://openalex.org/W2039157918","https://openalex.org/W2070771761","https://openalex.org/W2101234009","https://openalex.org/W2102632804","https://openalex.org/W2142804492","https://openalex.org/W2150990363","https://openalex.org/W2153470728","https://openalex.org/W2527994611","https://openalex.org/W2560021099","https://openalex.org/W2783034914","https://openalex.org/W2786162033","https://openalex.org/W2947815220","https://openalex.org/W2964805342","https://openalex.org/W3054225939","https://openalex.org/W4230940751","https://openalex.org/W4237335675","https://openalex.org/W6601696544","https://openalex.org/W6636915900","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2575897682","https://openalex.org/W2081797125","https://openalex.org/W2996079066","https://openalex.org/W1967312449","https://openalex.org/W1986094003","https://openalex.org/W2096044998","https://openalex.org/W1424383737","https://openalex.org/W3092043337","https://openalex.org/W3086201193","https://openalex.org/W2945511280"],"abstract_inverted_index":{"The":[0,94],"telecommunications":[1],"industry":[2],"makes":[3],"extensive":[4],"use":[5],"of":[6,82,90],"data":[7,21,25,61,84],"extracted":[8],"from":[9],"logs,":[10],"alarms,":[11],"traces,":[12],"diagnostics,":[13],"and":[14,29,40,58,62,68,76],"other":[15],"monitoring":[16],"devices.":[17],"Analyzing":[18],"the":[19,24,88,91,98],"generated":[20],"requires":[22,41],"that":[23,97],"be":[26],"parsed,":[27],"re-structured,":[28],"re-formatted.":[30],"Developing":[31],"custom":[32],"parsers":[33],"for":[34],"each":[35],"input":[36],"format":[37],"is":[38],"labor-intensive":[39],"domain":[42],"knowledge.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"describe":[48],"a":[49,80],"novel":[50],"unsupervised":[51],"text":[52],"processing":[53],"pipeline":[54],"to":[55,86],"automatically":[56],"detect":[57],"label":[59],"relevant":[60],"eliminate":[63],"noise":[64],"using":[65],"Levenshtein":[66],"similarity":[67,75],"Agglomerative":[69],"clustering.":[70],"We":[71],"experiment":[72],"with":[73],"different":[74],"clustering":[77],"algorithms":[78],"on":[79],"selection":[81],"common":[83],"formats":[85],"verify":[87],"accuracy":[89],"proposed":[92,99],"technique.":[93],"results":[95],"suggest":[96],"methodology":[100],"has":[101],"higher":[102],"accuracy.":[103]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}