{"id":"https://openalex.org/W4389518757","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.374","title":"Multimodal Embodied Plan Prediction Augmented with Synthetic Embodied Dialogue","display_name":"Multimodal Embodied Plan Prediction Augmented with Synthetic Embodied Dialogue","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518757","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.374"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.374","pdf_url":"https://aclanthology.org/2023.emnlp-main.374.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.emnlp-main.374.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041020656","display_name":"Aishwarya Padmakumar","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":true,"raw_author_name":"Aishwarya Padmakumar","raw_affiliation_strings":["Northeastern University","University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088122258","display_name":"Mert \u0130nan","orcid":"https://orcid.org/0000-0001-6972-411X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Mert Inan","raw_affiliation_strings":["University of Illinois Urbana-Champaign","Northeastern University"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041111343","display_name":"Spandana Gella","orcid":"https://orcid.org/0000-0003-2725-4476"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Spandana Gella","raw_affiliation_strings":["Northeastern University","University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029778136","display_name":"Patrick Lange","orcid":"https://orcid.org/0000-0003-3935-663X"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Patrick Lange","raw_affiliation_strings":["Northeastern University","University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["MX","US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-Tur","raw_affiliation_strings":["Northeastern University","University of Illinois Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041020656"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I87182695"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4456212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6114","last_page":"6131"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.8249546885490417},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.8055394887924194},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.640275239944458},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6257644295692444},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5598078370094299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510566234588623},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5291118025779724},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5025949478149414},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4635438621044159},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4607897698879242},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4307639002799988},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41493749618530273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3838120400905609},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10833975672721863},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07814350724220276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249546885490417},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8055394887924194},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.640275239944458},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6257644295692444},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5598078370094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510566234588623},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5291118025779724},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5025949478149414},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4635438621044159},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4607897698879242},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4307639002799988},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41493749618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3838120400905609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10833975672721863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07814350724220276},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.374","pdf_url":"https://aclanthology.org/2023.emnlp-main.374.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.374","pdf_url":"https://aclanthology.org/2023.emnlp-main.374.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518757.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W88050112","https://openalex.org/W561688239","https://openalex.org/W1969483458","https://openalex.org/W1975244201","https://openalex.org/W2035375323","https://openalex.org/W2054268394","https://openalex.org/W2062175565","https://openalex.org/W2120045257","https://openalex.org/W2130160035","https://openalex.org/W2147334703","https://openalex.org/W2156243072","https://openalex.org/W2168490009","https://openalex.org/W2337392266","https://openalex.org/W2482333547","https://openalex.org/W2507218956","https://openalex.org/W2586777479","https://openalex.org/W2603266952","https://openalex.org/W2784070054","https://openalex.org/W2784820185","https://openalex.org/W2787066086","https://openalex.org/W2787625232","https://openalex.org/W2799002257","https://openalex.org/W2884565639","https://openalex.org/W2950801649","https://openalex.org/W2959918500","https://openalex.org/W2963043030","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2971077754","https://openalex.org/W2979727876","https://openalex.org/W3034758614","https://openalex.org/W3034999214","https://openalex.org/W3036497058","https://openalex.org/W3040621713","https://openalex.org/W3042040243","https://openalex.org/W3104546989","https://openalex.org/W3106271432","https://openalex.org/W3106540028","https://openalex.org/W3203663566","https://openalex.org/W4214700710","https://openalex.org/W4221153228","https://openalex.org/W4224912544","https://openalex.org/W4286905705","https://openalex.org/W4287079536","https://openalex.org/W4287888476","https://openalex.org/W4293566037","https://openalex.org/W4294010056","https://openalex.org/W4307206775","https://openalex.org/W4312272037","https://openalex.org/W4312594400","https://openalex.org/W4385573572","https://openalex.org/W4385574172","https://openalex.org/W4389009467"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W4389520438","https://openalex.org/W4297445807"],"abstract_inverted_index":{"Embodied":[0],"task":[1],"completion":[2],"is":[3,96],"a":[4,10,31,42,48,102],"challenge":[5],"where":[6,36],"an":[7],"agent":[8,38,53],"in":[9],"simulated":[11],"environment":[12,15],"must":[13],"predict":[14],"actions":[16,40,54],"to":[17,104],"complete":[18],"tasks":[19],"based":[20],"on":[21,138],"natural":[22],"language":[23,67],"instructions":[24],"and":[25,57,98],"ego-centric":[26],"visual":[27],"observations.":[28],"We":[29,69,119],"propose":[30,101],"variant":[32],"of":[33,45,65,86],"this":[34,80],"problem":[35,81],"the":[37,62],"predicts":[39],"at":[41],"higher":[43],"level":[44],"abstraction":[46],"called":[47],"plan,":[49],"which":[50,109],"helps":[51],"make":[52],"more":[55],"interpretable":[56],"can":[58,75,125],"be":[59],"obtained":[60],"from":[61,130],"appropriate":[63],"prompting":[64],"large":[66],"models.":[68],"show":[70],"that":[71,121],"multimodal":[72,122],"transformer":[73,123],"models":[74,78,124,136],"outperform":[76],"language-only":[77,135],"for":[79,93,116],"but":[82],"fall":[83],"significantly":[84],"short":[85],"oracle":[87],"plans.":[88],"Since":[89],"collecting":[90],"human-human":[91,139],"dialogues":[92],"embodied":[94],"environments":[95],"expensive":[97],"time-consuming,":[99],"we":[100,110],"method":[103],"synthetically":[105],"generate":[106],"such":[107],"dialogues,":[108],"then":[111],"use":[112],"as":[113],"training":[114],"data":[115],"plan":[117],"prediction.":[118],"demonstrate":[120],"attain":[126],"strong":[127],"zero-shot":[128],"performance":[129],"our":[131],"synthetic":[132],"data,":[133],"outperforming":[134],"trained":[137],"data.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}