{"id":"https://openalex.org/W4412889759","doi":"https://doi.org/10.18653/v1/2025.acl-long.1467","title":"Predicting Implicit Arguments in Procedural Video Instructions","display_name":"Predicting Implicit Arguments in Procedural Video Instructions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889759","doi":"https://doi.org/10.18653/v1/2025.acl-long.1467"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1467","pdf_url":"https://aclanthology.org/2025.acl-long.1467.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1467.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076594514","display_name":"Anil Batra","orcid":"https://orcid.org/0000-0001-7470-9037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anil Batra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076169111","display_name":"Laura Sevilla-Lara","orcid":"https://orcid.org/0000-0001-8276-0094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Sevilla-Lara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024481540","display_name":"Marcus Rohrbach","orcid":"https://orcid.org/0000-0001-5908-7751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Rohrbach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054936589","display_name":"Frank Keller","orcid":"https://orcid.org/0000-0002-8242-4362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Keller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30399","last_page":"30419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7213000059127808,"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"}},"topics":[{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7213000059127808,"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":0.7307892441749573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34109365940093994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307892441749573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34109365940093994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1467","pdf_url":"https://aclanthology.org/2025.acl-long.1467.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1674d166-7618-4bbe-b938-998e8671a194","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1674d166-7618-4bbe-b938-998e8671a194","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Batra, A, Sevilla-Lara, L, Rohrbach, M & Keller, F 2025, Predicting Implicit Arguments in Procedural Video Instructions. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. vol. 1, 1467, Association for Computational Linguistics, Proceedings of the conference, Vienna, Austria, pp. 30399-30419, The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, 27/07/25. https://doi.org/10.18653/v1/2025.acl-long.1467","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1467","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1467","pdf_url":"https://aclanthology.org/2025.acl-long.1467.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889759.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Procedural":[0,29],"texts":[1],"help":[2],"AI":[3],"enhance":[4],"reasoning":[5],"about":[6],"context":[7],"and":[8,42,87,118,129,152],"action":[9],"sequences.":[10],"Transforming":[11],"these":[12],"into":[13],"Semantic":[14],"Role":[15],"Labeling":[16],"(SRL)":[17],"improves":[18],"understanding":[19],"of":[20,127],"individual":[21],"steps":[22],"by":[23],"identifying":[24],"predicate-argument":[25],"structure":[26],"like":[27],"verb,what,where/with.":[28],"instructions":[30],"are":[31],"highly":[32],"elliptic,":[33],"for":[34,150,155],"instance,":[35],"(i)":[36],"add":[37,44],"cucumber":[38,61],"to":[39,58,72,123],"the":[40,47,55,60,136],"bowl":[41],"(ii)":[43],"sliced":[45],"tomatoes,":[46],"second":[48],"step's":[49],"where":[50,59],"argument":[51],"is":[52],"inferred":[53],"from":[54,90,131],"context,":[56],"referring":[57],"was":[62],"placed.":[63],"Prior":[64],"SRL":[65],"benchmarks":[66,100],"often":[67],"miss":[68],"implicit":[69,86,125],"arguments,":[70],"leading":[71],"incomplete":[73],"understanding.":[74],"To":[75],"address":[76],"this,":[77],"we":[78,139],"introduce":[79],"Implicit-VidSRL,":[80],"a":[81,144,153],"dataset":[82,99],"that":[83,120],"necessitates":[84],"inferring":[85],"explicit":[88],"arguments":[89,126],"contextual":[91,103],"information":[92],"in":[93,111,148],"multimodal":[94,101,116],"cooking":[95],"procedures.":[96],"Our":[97],"proposed":[98],"models'":[102],"reasoning,":[104],"requiring":[105],"entity":[106],"tracking":[107],"through":[108],"visual":[109],"changes":[110],"recipes.":[112],"We":[113],"study":[114],"recent":[115],"LLMs":[117],"reveal":[119],"they":[121],"struggle":[122],"predict":[124],"what":[128],"where/with":[130],"multi-modal":[132],"procedural":[133],"data":[134],"given":[135],"verb.":[137],"Lastly,":[138],"propose":[140],"iSRL-Qwen2-VL,":[141],"which":[142],"achieves":[143],"17%":[145],"relative":[146],"improvement":[147],"F1-score":[149],"what-implicit":[151],"14.7%":[154],"where/with-implicit":[156],"semantic":[157],"roles":[158],"over":[159],"GPT-4o.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}