{"id":"https://openalex.org/W2387719207","doi":"https://doi.org/10.1145/2884781.2884862","title":"From word embeddings to document similarities for improved information retrieval in software engineering","display_name":"From word embeddings to document similarities for improved information retrieval in software engineering","publication_year":2016,"publication_date":"2016-05-13","ids":{"openalex":"https://openalex.org/W2387719207","doi":"https://doi.org/10.1145/2884781.2884862","mag":"2387719207"},"language":"en","primary_location":{"id":"doi:10.1145/2884781.2884862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","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/A5100348113","display_name":"Xin Ye","orcid":"https://orcid.org/0000-0002-6409-5331"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Ye","raw_affiliation_strings":["Ohio University Athens, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio University Athens, Ohio","institution_ids":["https://openalex.org/I4210106879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002208932","display_name":"Hui Shen","orcid":"https://orcid.org/0000-0002-5582-4555"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Shen","raw_affiliation_strings":["Ohio University Athens, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio University Athens, Ohio","institution_ids":["https://openalex.org/I4210106879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011411728","display_name":"Xiao Ma","orcid":"https://orcid.org/0000-0003-1288-3632"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Ma","raw_affiliation_strings":["Ohio University Athens, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio University Athens, Ohio","institution_ids":["https://openalex.org/I4210106879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020435927","display_name":"R\u0103zvan Bunescu","orcid":"https://orcid.org/0000-0003-2919-3566"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razvan Bunescu","raw_affiliation_strings":["Ohio University Athens, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio University Athens, Ohio","institution_ids":["https://openalex.org/I4210106879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101434532","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-1542-0257"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Ohio University Athens, Ohio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio University Athens, Ohio","institution_ids":["https://openalex.org/I4210106879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210106879"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":292,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"404","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9961000084877014,"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":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.8759661912918091},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5952120423316956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5752848982810974},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5457803606987},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.534955620765686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5271898508071899},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5054161548614502},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4974363148212433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4654226005077362},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4385855793952942},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4197996258735657},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4140966534614563},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24863091111183167},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11358919739723206},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.09102246165275574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8759661912918091},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5952120423316956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5752848982810974},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5457803606987},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.534955620765686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5271898508071899},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5054161548614502},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4974363148212433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4654226005077362},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4385855793952942},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4197996258735657},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4140966534614563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24863091111183167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11358919739723206},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.09102246165275574},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2884781.2884862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1532325895","https://openalex.org/W1566018662","https://openalex.org/W1588986231","https://openalex.org/W1614298861","https://openalex.org/W1928731475","https://openalex.org/W1977971855","https://openalex.org/W1983578042","https://openalex.org/W1985947101","https://openalex.org/W1986541713","https://openalex.org/W2000518393","https://openalex.org/W2004247102","https://openalex.org/W2014022233","https://openalex.org/W2017593508","https://openalex.org/W2018663431","https://openalex.org/W2026003524","https://openalex.org/W2035720976","https://openalex.org/W2040043446","https://openalex.org/W2047221353","https://openalex.org/W2049238280","https://openalex.org/W2050396504","https://openalex.org/W2050712820","https://openalex.org/W2058230372","https://openalex.org/W2063384185","https://openalex.org/W2086511124","https://openalex.org/W2089759055","https://openalex.org/W2100739938","https://openalex.org/W2105400090","https://openalex.org/W2110220994","https://openalex.org/W2115130131","https://openalex.org/W2116737258","https://openalex.org/W2117130368","https://openalex.org/W2122060876","https://openalex.org/W2125031621","https://openalex.org/W2125980283","https://openalex.org/W2131744502","https://openalex.org/W2139543149","https://openalex.org/W2141599568","https://openalex.org/W2141987989","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2161847731","https://openalex.org/W2251803266","https://openalex.org/W2882319491","https://openalex.org/W2997617958","https://openalex.org/W2998704965","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2128807628","https://openalex.org/W1555966012","https://openalex.org/W4234264766","https://openalex.org/W2415426693","https://openalex.org/W2135356905","https://openalex.org/W3028990185","https://openalex.org/W1869615134","https://openalex.org/W2154282042","https://openalex.org/W2114279702","https://openalex.org/W3200612347"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,144],"information":[3],"retrieval":[4],"techniques":[5],"to":[6,114,130,148],"search":[7,20],"tasks":[8],"in":[9,24,34,44,64,88,112,132],"software":[10,66],"engineering":[11],"is":[12,40],"made":[13],"difficult":[14],"by":[15,77],"the":[16,42,55,74,94,124],"lexical":[17,75],"gap":[18,76],"between":[19,57,118],"queries,":[21],"usually":[22,32],"expressed":[23,33],"natural":[25,79],"language":[26,80],"(e.g.":[27,36],"English),":[28],"and":[29,46,60,82,106,109,139],"retrieved":[30],"documents,":[31,104,108],"code":[35,83],"programming":[37,150],"languages).":[38],"This":[39],"often":[41],"case":[43],"bug":[45,136],"feature":[47],"location,":[48],"community":[49],"question":[50],"answering,":[51],"or":[52],"more":[53],"generally":[54],"communication":[56],"technical":[58],"personnel":[59],"non-technical":[61],"stake":[62],"holders":[63],"a":[65,89,133,140],"project.":[67],"In":[68,93],"this":[69],"paper,":[70],"we":[71],"propose":[72],"bridging":[73],"projecting":[78],"statements":[81],"snippets":[84],"as":[85],"meaning":[86],"vectors":[87],"shared":[90],"representation":[91],"space.":[92],"proposed":[95],"architecture,":[96],"word":[97],"embeddings":[98,128],"are":[99],"first":[100],"trained":[101],"on":[102],"API":[103,146],"tutorials,":[105],"reference":[107],"then":[110],"aggregated":[111],"order":[113],"estimate":[115],"semantic":[116],"similarities":[117],"documents.":[119],"Empirical":[120],"evaluations":[121],"show":[122],"that":[123],"learned":[125],"vector":[126],"space":[127],"lead":[129],"improvements":[131],"previously":[134],"explored":[135],"localization":[137],"task":[138,143],"newly":[141],"defined":[142],"linking":[145],"documents":[147],"computer":[149],"questions.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":43},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":52},{"year":2018,"cited_by_count":39},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}