{"id":"https://openalex.org/W4386475444","doi":"https://doi.org/10.1142/s0218194023500547","title":"ICG: A Machine Learning Benchmark Dataset and Baselines for Inline Code Comments Generation Task","display_name":"ICG: A Machine Learning Benchmark Dataset and Baselines for Inline Code Comments Generation Task","publication_year":2023,"publication_date":"2023-09-06","ids":{"openalex":"https://openalex.org/W4386475444","doi":"https://doi.org/10.1142/s0218194023500547"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194023500547","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500547","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge 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/A5061429963","display_name":"Xiaowei Zhang","orcid":"https://orcid.org/0000-0003-1481-5158"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-1481-5158","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443798","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0003-2352-2226"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lin Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-2352-2226","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005221755","display_name":"Weiqin Zou","orcid":"https://orcid.org/0000-0002-0913-1539"},"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":"Weiqin Zou","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0913-1539","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, P. R. China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004149127","display_name":"Yulu Cao","orcid":"https://orcid.org/0000-0002-6623-1165"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulu Cao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-6623-1165","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045631508","display_name":"Hao Ren","orcid":"https://orcid.org/0000-0002-0981-2852"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ren","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0981-2852","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101788794","display_name":"Zhi Wang","orcid":"https://orcid.org/0009-0009-2484-0796"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0009-0009-2484-0796","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360608","display_name":"Yanhui Li","orcid":"https://orcid.org/0000-0003-2282-7175"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-2282-7175","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031391841","display_name":"Yuming Zhou","orcid":"https://orcid.org/0000-0002-4645-2526"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Zhou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-4645-2526","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100443798"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.2331,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84296937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":"02","first_page":"331","last_page":"356"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9639999866485596,"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":0.8620275259017944},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5581837892532349},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.5451310873031616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5315418243408203},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5218497514724731},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5084347128868103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48805201053619385},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4641944169998169},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4482540786266327},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.431610643863678},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.4269822835922241},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4171423316001892},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3936401605606079},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3617861270904541},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.30505627393722534},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2603192925453186},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.21403002738952637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620275259017944},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5581837892532349},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5451310873031616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5315418243408203},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5218497514724731},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5084347128868103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48805201053619385},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4641944169998169},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4482540786266327},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.431610643863678},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.4269822835922241},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4171423316001892},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3936401605606079},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3617861270904541},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.30505627393722534},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2603192925453186},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.21403002738952637},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194023500547","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s0218194023500547","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2034209539","https://openalex.org/W2070111972","https://openalex.org/W2081749632","https://openalex.org/W2082160726","https://openalex.org/W2090398160","https://openalex.org/W2123333323","https://openalex.org/W2125055259","https://openalex.org/W2133333349","https://openalex.org/W2164577291","https://openalex.org/W2168382229","https://openalex.org/W2366532918","https://openalex.org/W2395122565","https://openalex.org/W2406310821","https://openalex.org/W2516621648","https://openalex.org/W2579161546","https://openalex.org/W2605807148","https://openalex.org/W2724503592","https://openalex.org/W2741561716","https://openalex.org/W2767331170","https://openalex.org/W2807964941","https://openalex.org/W2884276923","https://openalex.org/W2888312537","https://openalex.org/W2888557792","https://openalex.org/W2888651608","https://openalex.org/W2911964244","https://openalex.org/W2941068928","https://openalex.org/W2945876109","https://openalex.org/W2949297108","https://openalex.org/W2964194820","https://openalex.org/W2964322208","https://openalex.org/W3001085422","https://openalex.org/W3024989870","https://openalex.org/W3034999214","https://openalex.org/W3036685832","https://openalex.org/W3039512627","https://openalex.org/W3091730360","https://openalex.org/W3107676683","https://openalex.org/W3186816466","https://openalex.org/W3194328616","https://openalex.org/W4214548153","https://openalex.org/W4249122235","https://openalex.org/W4313043838","https://openalex.org/W4320490961"],"related_works":["https://openalex.org/W2969257295","https://openalex.org/W3006945192","https://openalex.org/W1976804602","https://openalex.org/W2390554102","https://openalex.org/W2909969119","https://openalex.org/W2098629748","https://openalex.org/W656101134","https://openalex.org/W3135060008","https://openalex.org/W2390085541","https://openalex.org/W2161188088"],"abstract_inverted_index":{"As":[0,34,174],"a":[1,56,114,129,154,171,175,179,197,202],"fundamental":[2],"component":[3],"of":[4,18,36,82,131,188,211,214,244,251],"software":[5],"documentation,":[6],"code":[7,31,37,40,46,83,143,192,221,271],"comments":[8,21,41,53,66,99,141,190],"could":[9,162],"help":[10,257],"developers":[11,74],"comprehend":[12],"and":[13,59,79,142,191,200,204,227,254,259],"maintain":[14],"programs.":[15],"Several":[16],"datasets":[17],"method":[19,51,63,87],"header":[20,52],"have":[22],"been":[23],"proposed":[24],"in":[25,55,70,85,170,220],"previous":[26],"studies":[27],"for":[28,45,97,247],"machine":[29,118],"learning-based":[30],"comment":[32,263],"generation.":[33],"part":[35],"comments,":[38,216,236],"inline":[39,65,98,132,140,189,215,235,262],"are":[42,67,88],"also":[43,268],"crucial":[44],"understanding":[47,272],"activities.":[48,273],"However,":[49],"unlike":[50],"written":[54,69],"standard":[57],"format":[58],"describing":[60],"the":[61,86,167,209,242,245],"whole":[62],"code,":[64],"often":[68],"arbitrary":[71],"formats":[72],"by":[73],"due":[75],"to":[76,108,116,157,165,207,232,240],"timelines":[77],"pressures":[78],"different":[80,212],"aspects":[81],"snippets":[84,144],"described.":[89],"Currently,":[90],"there":[91],"is":[92],"no":[93],"large-scale":[94,180],"dataset":[95,115,182],"used":[96,164],"generation":[100,264],"considering":[101],"these.":[102],"Hence,":[103],"this":[104,135],"naturally":[105],"inspires":[106],"us":[107],"explore":[109,208],"whether":[110],"we":[111,137,152,177,225],"can":[112,256],"construct":[113,178],"foster":[117],"learning":[119],"research":[120],"that":[121],"not":[122],"only":[123],"performs":[124],"fine-grained":[125,172],"noise-cleaning":[126],"but":[127],"conducts":[128],"taxonomy":[130,199],"comments.":[133],"To":[134],"end,":[136],"first":[138],"collect":[139],"from":[145],"8000":[146],"Java":[147],"projects":[148],"on":[149],"GitHub.":[150],"Then,":[151],"conduct":[153,201],"manual":[155,205],"review":[156],"obtain":[158],"heuristic":[159],"rules,":[160],"which":[161,266],"be":[163],"clean":[166],"data":[168],"noise":[169],"manner.":[173],"result,":[176],"benchmark":[181,246,253],"named":[183],"ICG":[184],"with":[185],"5,740,770":[186],"pairs":[187],"snippets.":[193],"We":[194],"then":[195],"build":[196],"comprehensive":[198],"statistical":[203],"analysis":[206],"performances":[210],"categories":[213],"such":[217,237],"as":[218,238],"helpfulness":[219],"understanding.":[222],"After":[223],"that,":[224],"provide":[226],"compare":[228],"several":[229],"baseline":[230],"models":[231],"automatically":[233],"generate":[234],"CodeBERT,":[239],"enhance":[241],"usability":[243],"researchers.":[248],"The":[249],"availability":[250],"our":[252],"baselines":[255],"develop":[258],"validate":[260],"new":[261],"methods,":[265],"would":[267],"further":[269],"facilitate":[270]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
