{"id":"https://openalex.org/W3101041928","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.443","title":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","display_name":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3101041928","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.443","mag":"3101041928"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.443","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.443.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.emnlp-main.443.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100733463","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-5484-0895"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Google Research, Mountain View, CA 94043, USA","Georgia Tech, Atlanta, GA 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438769","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-1583-641X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Georgia Tech, Atlanta, GA 30332, USA","Google Research, Mountain View, CA 94043, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025887224","display_name":"Luheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luheng He","raw_affiliation_strings":["Google Research, Mountain View, CA 94043, USA","Georgia Tech, Atlanta, GA 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048789563","display_name":"Jingjie Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjie Zheng","raw_affiliation_strings":["Google Research, Mountain View, CA 94043, USA","Georgia Tech, Atlanta, GA 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339431","display_name":"Hong Li","orcid":"https://orcid.org/0000-0003-1353-7838"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Li","raw_affiliation_strings":["Georgia Tech, Atlanta, GA 30332, USA","Google Research, Mountain View, CA 94043, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101484540","display_name":"Zhiwei Guan","orcid":"https://orcid.org/0000-0001-9908-3755"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwei Guan","raw_affiliation_strings":["Georgia Tech, Atlanta, GA 30332, USA","Google Research, Mountain View, CA 94043, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Google Research, Mountain View, CA 94043, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5495","last_page":"5510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9958999752998352,"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/closed-captioning","display_name":"Closed captioning","score":0.940097451210022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8894407749176025},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7202685475349426},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.6259593963623047},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.614298403263092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.613347589969635},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6036341190338135},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5350376963615417},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5281457901000977},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.5234588980674744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5042134523391724},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4752506911754608},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4518659710884094},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42585518956184387},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3864554166793823},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15419867634773254},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13448715209960938},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13232830166816711},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0774279534816742}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.940097451210022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8894407749176025},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7202685475349426},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6259593963623047},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.614298403263092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.613347589969635},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6036341190338135},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5350376963615417},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5281457901000977},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.5234588980674744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042134523391724},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4752506911754608},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4518659710884094},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42585518956184387},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3864554166793823},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15419867634773254},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13448715209960938},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13232830166816711},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0774279534816742},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.443","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.443.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.emnlp-main.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.443","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.443.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3101041928.pdf","grobid_xml":"https://content.openalex.org/works/W3101041928.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2025768430","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2142112143","https://openalex.org/W2163605009","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2506483933","https://openalex.org/W2508429489","https://openalex.org/W2610917376","https://openalex.org/W2765387833","https://openalex.org/W2765874585","https://openalex.org/W2791213089","https://openalex.org/W2886641317","https://openalex.org/W2896625930","https://openalex.org/W2897267527","https://openalex.org/W2913974265","https://openalex.org/W2942076676","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964145825","https://openalex.org/W3034392229","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3009270862","https://openalex.org/W2018992341","https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2900126711","https://openalex.org/W4285240985","https://openalex.org/W4225162083","https://openalex.org/W3202115945"],"abstract_inverted_index":{"Natural":[0],"language":[1,40,73,148],"descriptions":[2,23,41],"of":[3,56,100,115,121],"user":[4,57,150],"interface":[5],"(UI)":[6],"elements":[7,44,83],"such":[8],"as":[9,110,112,130,132],"alternative":[10],"text":[11],"are":[12,24],"crucial":[13],"for":[14,37,42,64,79,140],"accessibility":[15],"and":[16,52,94,96,127,149],"language-based":[17],"interaction":[18],"in":[19,27],"general.":[20],"Yet,":[21],"these":[22],"constantly":[25],"missing":[26],"mobile":[28],"UIs.":[29],"We":[30,59,89],"propose":[31],"widget":[32,65],"captioning,":[33],"a":[34,61,98,137],"novel":[35,142],"task":[36,125,145],"automatically":[38],"generating":[39],"UI":[43,82,87],"from":[45],"multimodal":[46,143],"input":[47],"including":[48],"both":[49],"the":[50,53,92,113,119,128],"image":[51],"structural":[54],"representations":[55],"interfaces.":[58,151],"collected":[60],"largescale":[62],"dataset":[63,70,129],"captioning":[66,144],"with":[67],"crowdsourcing.":[68],"Our":[69],"contains":[71],"162,859":[72],"phrases":[74],"created":[75],"by":[76],"human":[77],"workers":[78],"annotating":[80],"61,285":[81],"across":[84],"21,750":[85],"unique":[86],"screens.":[88],"thoroughly":[90],"analyze":[91],"dataset,":[93],"train":[95],"evaluate":[97],"set":[99],"deep":[101],"model":[102],"configurations":[103],"to":[104],"investigate":[105],"how":[106],"each":[107],"feature":[108],"modality":[109],"well":[111,131],"choice":[114],"learning":[116],"strategies":[117],"impact":[118],"quality":[120],"predicted":[122],"captions.":[123],"The":[124],"formulation":[126],"our":[133],"benchmark":[134],"models":[135],"contribute":[136],"solid":[138],"basis":[139],"this":[141],"that":[146],"connects":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}