{"id":"https://openalex.org/W3153193882","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.165","title":"Visual Goal-Step Inference using wikiHow","display_name":"Visual Goal-Step Inference using wikiHow","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3153193882","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.165","mag":"3153193882"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.165","pdf_url":"https://aclanthology.org/2021.emnlp-main.165.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.165.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101841177","display_name":"Yue Yang","orcid":"https://orcid.org/0000-0003-0051-0310"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Yang","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084018235","display_name":"Artemis Panagopoulou","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Artemis Panagopoulou","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057851690","display_name":"Qing Lyu","orcid":"https://orcid.org/0000-0002-9824-0170"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Lyu","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425466","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-8752-8315"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205261","display_name":"Mark Yatskar","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Yatskar","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068508539","display_name":"Chris Callison-Burch","orcid":"https://orcid.org/0000-0001-8196-1943"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Callison-Burch","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania","#N#               * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101841177"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.1314,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4433152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2167","last_page":"2179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8062943816184998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7792193293571472},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7481892108917236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6711772680282593},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.566641092300415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5020437240600586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39194583892822266}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8062943816184998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792193293571472},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7481892108917236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6711772680282593},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.566641092300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5020437240600586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39194583892822266},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.165","pdf_url":"https://aclanthology.org/2021.emnlp-main.165.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.05845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05845","pdf_url":"https://arxiv.org/pdf/2104.05845","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2104.05845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.05845","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.165","pdf_url":"https://aclanthology.org/2021.emnlp-main.165.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G248152329","display_name":null,"funder_award_id":"1928631","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5487362199","display_name":null,"funder_award_id":"2019-19051600004","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G7219570620","display_name":"Development of an Undergraduate Laser Spectroscopy Course","funder_award_id":"9051600","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7857641858","display_name":"The Eukaryotic Core","funder_award_id":"0516000","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3153193882.pdf","grobid_xml":"https://content.openalex.org/works/W3153193882.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2050482109","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2123024445","https://openalex.org/W2183341477","https://openalex.org/W2463955103","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2798801105","https://openalex.org/W2899663614","https://openalex.org/W2963033987","https://openalex.org/W2963159690","https://openalex.org/W2963758027","https://openalex.org/W2963775347","https://openalex.org/W2964094654","https://openalex.org/W2964121744","https://openalex.org/W2970231061","https://openalex.org/W2978234544","https://openalex.org/W2984008963","https://openalex.org/W2998702515","https://openalex.org/W3019501371","https://openalex.org/W3102173443","https://openalex.org/W3103543556","https://openalex.org/W3114186958","https://openalex.org/W3155173317"],"related_works":["https://openalex.org/W149980","https://openalex.org/W11144228","https://openalex.org/W592020","https://openalex.org/W11991885","https://openalex.org/W10910819","https://openalex.org/W14230040","https://openalex.org/W12563130","https://openalex.org/W10596858","https://openalex.org/W9171921","https://openalex.org/W6630852"],"abstract_inverted_index":{"Understanding":[0],"what":[1],"sequence":[2],"of":[3,28,58,76],"steps":[4],"are":[5],"needed":[6],"to":[7,105],"complete":[8],"a":[9,47,51,62,69],"goal":[10,53],"can":[11,101],"help":[12],"artificial":[13],"intelligence":[14],"systems":[15],"reason":[16],"about":[17,123],"human":[18,80],"activities.":[19],"Past":[20],"work":[21],"in":[22],"NLP":[23],"has":[24],"examined":[25],"the":[26,35,40,94,111],"task":[27,86,118],"goal-step":[29],"inference":[30],"for":[31,89],"text.":[32],"We":[33,38],"introduce":[34],"visual":[36],"analogue.":[37],"propose":[39],"Visual":[41],"Goal-Step":[42],"Inference":[43],"(VGSI)":[44],"task,":[45],"where":[46],"model":[48],"is":[49,87],"given":[50],"textual":[52],"and":[54],"must":[55],"choose":[56],"which":[57],"four":[59],"images":[60,78],"represents":[61],"plausible":[63],"step":[64],"towards":[65],"that":[66,84],"goal.":[67],"With":[68],"new":[70],"dataset":[71],"harvested":[72],"from":[73,98],"wikiHow":[74],"consisting":[75],"772,277":[77],"representing":[79],"actions,":[81],"we":[82],"show":[83],"our":[85,99],"challenging":[88],"state-of-theart":[90],"multimodal":[91,95,121],"models.":[92],"Moreover,":[93],"representation":[96],"learned":[97],"data":[100],"be":[102],"effectively":[103],"transferred":[104],"other":[106],"datasets":[107],"like":[108],"HowTo100m,":[109],"increasing":[110],"VGSI":[112],"accuracy":[113],"by":[114],"15":[115],"-20%.":[116],"Our":[117],"will":[119],"facilitate":[120],"reasoning":[122],"procedural":[124],"events.":[125]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}