{"id":"https://openalex.org/W4412889519","doi":"https://doi.org/10.18653/v1/2025.acl-short.30","title":"A Little Human Data Goes A Long Way","display_name":"A Little Human Data Goes A Long Way","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889519","doi":"https://doi.org/10.18653/v1/2025.acl-short.30"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-short.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.30","pdf_url":"https://aclanthology.org/2025.acl-short.30.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 2: Short 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-short.30.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031475293","display_name":"Dhananjay Ashok","orcid":"https://orcid.org/0000-0001-7500-3730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhananjay Ashok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000874697","display_name":"Jonathan May","orcid":"https://orcid.org/0000-0002-5284-477X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan May","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.17010000348091125,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.17010000348091125,"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/computer-science","display_name":"Computer science","score":0.6138525009155273},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32950255274772644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6138525009155273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32950255274772644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-short.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.30","pdf_url":"https://aclanthology.org/2025.acl-short.30.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 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-short.30","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.30","pdf_url":"https://aclanthology.org/2025.acl-short.30.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 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889519.pdf","grobid_xml":"https://content.openalex.org/works/W4412889519.grobid-xml"},"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":{"Faced":[0],"with":[1,54],"an":[2,115],"expensive":[3],"human":[4,29,99,112,129,142],"annotation":[5,30,130,143],"process,":[6],"creators":[7],"of":[8,37,65,109,117,157],"NLP":[9],"systems":[10],"increasingly":[11],"turn":[12],"to":[13,23,63,79,152],"synthetic":[14,25,38,55,88,120],"data":[15,26,39,53,68,89,101,113],"generation.While":[16],"this":[17],"method":[18],"shows":[19],"promise,":[20],"the":[21,35,66,75,106,158],"extent":[22],"which":[24,128],"can":[27,90],"replace":[28],"is":[31,146,149],"poorly":[32],"understood.We":[33],"investigate":[34],"use":[36],"in":[40],"Fact":[41],"Verification":[42],"(FV)":[43],"and":[44,122],"Evidencebased":[45],"Question":[46],"Answering":[47],"(QA)":[48],"by":[49,93],"incrementally":[50],"replacing":[51,61,74],"human-generated":[52],"points":[56],"on":[57,86],"eight":[58],"diverse":[59],"datasets.Strikingly,":[60],"up":[62],"90%":[64],"training":[67],"only":[69],"marginally":[70],"decreases":[71],"performance,":[72],"but":[73],"final":[76],"10%":[77],"leads":[78],"severe":[80],"declines.We":[81],"find":[82],"that":[83,104,139],"models":[84],"trained":[85],"purely":[87],"be":[91,132],"improved":[92],"including":[94],"as":[95,97],"few":[96],"125":[98],"generated":[100],"points.We":[102],"show":[103],"matching":[105],"performance":[107],"gain":[108],"a":[110,133,154],"little":[111],"requires":[114],"order":[116],"magnitude":[118],"more":[119,134],"data,":[121],"then":[123],"estimate":[124],"price":[125],"ratios":[126],"at":[127,144],"would":[131],"costeffective":[135],"solution.Our":[136],"results":[137],"suggest":[138],"even":[140],"when":[141],"scale":[145],"infeasible,":[147],"there":[148],"great":[150],"value":[151],"having":[153],"small":[155],"proportion":[156],"dataset":[159],"being":[160],"human-generated.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}