{"id":"https://openalex.org/W4312931032","doi":"https://doi.org/10.1109/tse.2022.3227559","title":"BEQAIN: An Effective and Efficient Identifier Normalization Approach With BERT and the Question Answering System","display_name":"BEQAIN: An Effective and Efficient Identifier Normalization Approach With BERT and the Question Answering System","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4312931032","doi":"https://doi.org/10.1109/tse.2022.3227559"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2022.3227559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3227559","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5005439960","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0000-0002-8437-6640"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingxuan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406620","display_name":"Siyuan Liu","orcid":"https://orcid.org/0000-0002-0946-4683"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Liu","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027202117","display_name":"Lina Gong","orcid":"https://orcid.org/0000-0002-5272-6706"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Gong","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765845","display_name":"Haoxiang Zhang","orcid":"https://orcid.org/0000-0002-3921-1724"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haoxiang Zhang","raw_affiliation_strings":["Queen's University, Kingston, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025184050","display_name":"Zhiqiu Huang","orcid":"https://orcid.org/0000-0001-6843-1892"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiu Huang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002119636","display_name":"He Jiang","orcid":"https://orcid.org/0000-0001-8674-4948"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Jiang","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005439960"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":3.8199,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9430883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":"4","first_page":"2597","last_page":"2620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9976000189781189,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9948999881744385,"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/identifier","display_name":"Identifier","score":0.961679220199585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8456989526748657},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6487450003623962},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.5900633335113525},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5419713854789734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43994638323783875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4362906217575073},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4351547956466675},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.43002673983573914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3762311637401581},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27667948603630066}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.961679220199585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456989526748657},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6487450003623962},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5900633335113525},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5419713854789734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43994638323783875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4362906217575073},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4351547956466675},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.43002673983573914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3762311637401581},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27667948603630066},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2022.3227559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3227559","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2420032213","display_name":null,"funder_award_id":"61902181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3427093674","display_name":null,"funder_award_id":"62032004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322438","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1972420078","https://openalex.org/W1973681806","https://openalex.org/W1996842335","https://openalex.org/W2018360580","https://openalex.org/W2022675432","https://openalex.org/W2040664452","https://openalex.org/W2050219469","https://openalex.org/W2077537588","https://openalex.org/W2089066875","https://openalex.org/W2099294614","https://openalex.org/W2108036122","https://openalex.org/W2113837606","https://openalex.org/W2128737833","https://openalex.org/W2140609933","https://openalex.org/W2154027310","https://openalex.org/W2156050524","https://openalex.org/W2165049137","https://openalex.org/W2165664509","https://openalex.org/W2165995531","https://openalex.org/W2170116643","https://openalex.org/W2171238733","https://openalex.org/W2297781517","https://openalex.org/W2380058981","https://openalex.org/W2618735982","https://openalex.org/W2742136054","https://openalex.org/W2749337727","https://openalex.org/W2891551983","https://openalex.org/W2896457183","https://openalex.org/W2898435572","https://openalex.org/W2899020304","https://openalex.org/W2901397932","https://openalex.org/W2938075706","https://openalex.org/W2943748428","https://openalex.org/W2962784628","https://openalex.org/W2963739249","https://openalex.org/W2963935794","https://openalex.org/W2973461969","https://openalex.org/W2993817625","https://openalex.org/W3012193977","https://openalex.org/W3022269570","https://openalex.org/W3027231523","https://openalex.org/W3043493273","https://openalex.org/W3088111612","https://openalex.org/W3098598077","https://openalex.org/W3101714027","https://openalex.org/W3147782219","https://openalex.org/W3163046698","https://openalex.org/W3194328616","https://openalex.org/W3197635772","https://openalex.org/W4213258200","https://openalex.org/W4231520479","https://openalex.org/W4240565647","https://openalex.org/W4288076432","https://openalex.org/W6682082992","https://openalex.org/W6739901393","https://openalex.org/W6753163642","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2343500026","https://openalex.org/W2319837024","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W2051731675","https://openalex.org/W2033159440"],"abstract_inverted_index":{"As":[0],"one":[1,331],"of":[2,11,18,96,100,138,184,253,273,295,311,326],"the":[3,9,48,72,79,94,124,162,182,192,207,213,219,249,269,277,293,303,309,322,340],"most":[4],"important":[5],"resources":[6],"to":[7,41,46,89,115,154,180,190,205,217,240,247,346],"express":[8],"semantics":[10],"source":[12,34,86],"code,":[13],"identifiers":[14,52,83,117,156],"are":[15,225],"usually":[16],"composed":[17,137],"several":[19,67],"common":[20],"or":[21],"domain-specific":[22],"terms":[23],"and":[24,32,84,109,122,147,160,176,186,211,251,275,288],"abbreviations,":[25],"thus":[26],"heavily":[27],"hindering":[28],"developers":[29],"from":[30,93,143],"analyzing":[31],"comprehending":[33],"code.":[35],"Hence,":[36],"it":[37,236],"is":[38,135,169,233,328],"very":[39],"necessary":[40],"normalize":[42,90,241],"identifiers,":[43,91],"which":[44,134],"aims":[45],"align":[47],"vocabulary":[49],"found":[50,57],"in":[51,58,71,82,283,297,313],"with":[53,172,260],"natural":[54],"language":[55],"words":[56,121],"other":[59,348],"software":[60],"artifacts.":[61],"Even":[62],"though":[63],"researchers":[64],"have":[65],"proposed":[66],"identifier":[68,111,163,193,298,344],"normalization":[69,112,324,345],"approaches":[70,75],"literature,":[73],"these":[74],"only":[76],"rely":[77],"on":[78,318],"lexical":[80],"information":[81,306],"related":[85],"code":[87],"entities":[88],"suffering":[92],"lack":[95],"deep":[97,131],"semantic":[98],"understanding":[99],"identifiers.":[101,242,285],"In":[102,320],"this":[103],"paper,":[104],"we":[105,334],"propose":[106],"an":[107],"effective":[108],"efficient":[110],"approach":[113,280],"BEQAIN":[114,128,197,232,254,267,296,312,327],"split":[116],"into":[118,157],"their":[119],"composing":[120],"expand":[123],"enclosed":[125],"abbreviations.":[126,230],"Specifically,":[127],"employs":[129,199],"a":[130,139,148,173,177,200],"learning":[132],"model,":[133],"mainly":[136],"Bidirectional":[140],"Encoder":[141],"Representation":[142],"Transformers":[144],"(BERT)":[145],"layer":[146,153],"Conditional":[149],"Random":[150],"Fields":[151],"(CRF)":[152],"embed":[155],"low-level":[158],"vectors":[159],"learn":[161,206],"splitting":[164,194,299],"patterns.":[165],"The":[166,286],"BERT-CRF":[167],"network":[168],"also":[170,198,335],"combined":[171],"pre-processing":[174,287],"component":[175,179],"post-processing":[178,289],"resolve":[181],"problems":[183],"over-splitting":[185],"under-splitting":[187],"so":[188],"as":[189],"improve":[191,292,308],"performance.":[195],"Furthermore,":[196],"Question":[201],"Answering":[202],"(Q&A)":[203],"system":[204],"abbreviation":[208,314],"expansion":[209,222,315],"mappings":[210],"leverages":[212],"current":[214],"programming":[215,304],"context":[216,305],"determine":[218],"exactly":[220],"correct":[221],"when":[223],"there":[224],"multiple":[226],"expansions":[227],"for":[228,339,343],"specific":[229],"After":[231],"fully":[234],"trained,":[235],"can":[237],"be":[238],"used":[239],"We":[243],"conduct":[244],"extensive":[245],"experiments":[246],"validate":[248],"effectiveness":[250],"efficiency":[252],"over":[255],"two":[256],"publicly":[257],"available":[258],"datasets":[259],"nine":[261],"projects.":[262],"Experimental":[263],"results":[264],"show":[265],"that":[266],"achieves":[268],"overall":[270],"average":[271,323],"Accuracy":[272,294,310],"80.20%":[274],"outperforms":[276],"existing":[278],"state-of-the-art":[279],"by":[281,300,316],"9.88%":[282],"normalizing":[284],"components":[290],"could":[291,307],"11.70%.":[301],"Employing":[302],"11.15%":[317],"average.":[319],"addition,":[321],"time":[325],"less":[329],"than":[330],"second.":[332],"Finally,":[333],"discuss":[336],"some":[337],"observations":[338],"road":[341],"ahead":[342],"inspire":[347],"researchers.":[349]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}