{"id":"https://openalex.org/W4318147471","doi":"https://doi.org/10.1109/bigdata55660.2022.10020825","title":"Fine-Tuning BERT-based Language Models for Duplicate Trouble Report Retrieval","display_name":"Fine-Tuning BERT-based Language Models for Duplicate Trouble Report Retrieval","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318147471","doi":"https://doi.org/10.1109/bigdata55660.2022.10020825"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020825","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5050017351","display_name":"Nathan S. Bosch","orcid":null},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Nathan Bosch","raw_affiliation_strings":["Ericsson AB,GFTL GAIA,Stockholm,Sweden","KTH Royal Institute of Technology, Stockholm, Sweden","GFTL GAIA, Ericsson AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Ericsson AB,GFTL GAIA,Stockholm,Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"GFTL GAIA, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032177702","display_name":"Serveh Shalmashi","orcid":"https://orcid.org/0000-0002-2370-4567"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Serveh Shalmashi","raw_affiliation_strings":["Ericsson AB,GFTL GAIA,Stockholm,Sweden","GFTL GAIA, Ericsson AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Ericsson AB,GFTL GAIA,Stockholm,Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"GFTL GAIA, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064453204","display_name":"Forough Yaghoubi","orcid":"https://orcid.org/0000-0001-6435-106X"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Forough Yaghoubi","raw_affiliation_strings":["Ericsson AB,GFTL GAIA,Stockholm,Sweden","GFTL GAIA, Ericsson AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Ericsson AB,GFTL GAIA,Stockholm,Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"GFTL GAIA, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079664374","display_name":"Henrik Holm","orcid":"https://orcid.org/0000-0002-6895-6493"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Henrik Holm","raw_affiliation_strings":["Ericsson AB,GFTL GAIA,Stockholm,Sweden","GFTL GAIA, Ericsson AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Ericsson AB,GFTL GAIA,Stockholm,Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"GFTL GAIA, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003754421","display_name":"Fitsum Gaim","orcid":"https://orcid.org/0000-0003-1304-9594"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fitsum Gaim","raw_affiliation_strings":["Ericsson AB,GFTL GAIA,Stockholm,Sweden","GFTL GAIA, Ericsson AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Ericsson AB,GFTL GAIA,Stockholm,Sweden","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"GFTL GAIA, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012596151","display_name":"Amir H. Payberah","orcid":"https://orcid.org/0000-0002-2748-8929"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Amir H. Payberah","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden","KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5050017351"],"corresponding_institution_ids":["https://openalex.org/I1306339040","https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":1.1652,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82163573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4737","last_page":"4745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9789999723434448,"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/generalizability-theory","display_name":"Generalizability theory","score":0.9104150533676147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8271141052246094},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6488832235336304},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5676267147064209},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4871651828289032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4552615284919739},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4298102855682373},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4291125535964966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39626026153564453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33573827147483826}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9104150533676147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271141052246094},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6488832235336304},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5676267147064209},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4871651828289032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4552615284919739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4298102855682373},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4291125535964966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39626026153564453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33573827147483826},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020825","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W1844261860","https://openalex.org/W2036963181","https://openalex.org/W2060277733","https://openalex.org/W2086511124","https://openalex.org/W2165698076","https://openalex.org/W2560647685","https://openalex.org/W2766284073","https://openalex.org/W2783640434","https://openalex.org/W2895752714","https://openalex.org/W2896457183","https://openalex.org/W2922386288","https://openalex.org/W2951434086","https://openalex.org/W2951534261","https://openalex.org/W2953958347","https://openalex.org/W2963026768","https://openalex.org/W2964067969","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2980708516","https://openalex.org/W2982596739","https://openalex.org/W3021397474","https://openalex.org/W3034238904","https://openalex.org/W3080427797","https://openalex.org/W3091322135","https://openalex.org/W3098851962","https://openalex.org/W3099700870","https://openalex.org/W3118668786","https://openalex.org/W3137216496","https://openalex.org/W3154224745","https://openalex.org/W3208821253","https://openalex.org/W4206396334","https://openalex.org/W4252076394","https://openalex.org/W4295883599","https://openalex.org/W6639024717","https://openalex.org/W6672077861","https://openalex.org/W6677258307","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6755207826","https://openalex.org/W6764357534","https://openalex.org/W6766673545","https://openalex.org/W6769185743","https://openalex.org/W6779872132","https://openalex.org/W7010491546","https://openalex.org/W7064175541"],"related_works":["https://openalex.org/W2008630378","https://openalex.org/W2118717649","https://openalex.org/W1958015814","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406"],"abstract_inverted_index":{"In":[0,80],"large":[1],"software-intensive":[2],"organizations,":[3],"trouble":[4],"reports":[5],"(TRs)":[6],"are":[7],"heavily":[8],"involved":[9],"in":[10],"reporting,":[11],"analyzing,":[12],"and":[13,23,43,111,139],"resolving":[14],"faults.":[15],"Due":[16],"to":[17,32,41,75,77,88,102,116,131],"the":[18,37,97,127],"scale":[19],"of":[20],"modern":[21],"organizations":[22],"products,":[24],"multiple":[25],"people":[26],"independently":[27],"often":[28],"identify":[29,42],"faults,":[30],"leading":[31],"duplicate":[33,46,108],"TRs.":[34,79],"To":[35],"mitigate":[36],"additional":[38],"manual":[39],"effort":[40],"resolve":[44],"these":[45],"TRs,":[47],"prior":[48],"work":[49],"at":[50],"Ericsson":[51],"focused":[52],"on":[53,107,134],"developing":[54],"a":[55,66],"2-stage":[56],"BERT-based":[57,98],"retrieval":[58,100],"system":[59],"for":[60],"identifying":[61],"similar":[62],"TRs":[63],"when":[64],"provided":[65],"new":[67],"fault":[68],"observation.":[69],"This":[70],"approach,":[71],"although":[72],"powerful,":[73],"struggled":[74],"generalize":[76],"out-of-domain":[78,117],"this":[81],"paper,":[82],"we":[83],"evaluate":[84],"several":[85],"fine-tuning":[86,128],"strategies":[87],"integrate":[89],"domain":[90],"knowledge":[91],"further,":[92],"notably":[93],"telecommunications":[94],"knowledge,":[95],"into":[96,126],"TR":[99,109,118],"models":[101,129],"(i)":[103],"attain":[104],"better":[105],"performance":[106,138],"retrieval/identification":[110],"(ii)":[112],"improve":[113],"model":[114,137,140],"generalizability":[115],"data.":[119],"We":[120],"find":[121],"that":[122],"adding":[123],"domain-specific":[124],"data":[125],"led":[130],"improved":[132],"results":[133],"both":[135],"overall":[136],"generalizability.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}