{"id":"W3173967374","doi":"10.18653/v1/2021.acl-long.108","title":"Automated Generation of Storytelling Vocabulary from Photographs for use in AAC","year":2021,"lang":"en","type":"article","venue":"","topic":"Assistive Technology in Communication and Mobility","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds de recherche du Québec – Nature et technologies; AGE-WELL","keywords":"Storytelling; Vocabulary; Computer science; Computational linguistics; Joint (building); Natural language processing; Volume (thermodynamics); Computer graphics (images); Linguistics; Artificial intelligence; Library science; Engineering; Architectural engineering; Narrative; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003542396,0.00005984631,0.0001639798,0.00007662192,0.0001519181,0.000001995351,0.0001029304,0.0002108296,0.0002978893],"category_scores_gemma":[0.0003666039,0.00005823006,0.00004214474,0.0001934636,0.0000543427,0.00005909518,0.00007111883,0.0002283015,0.000007931691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005704229,"about_ca_system_score_gemma":0.0001619423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008029344,"about_ca_topic_score_gemma":0.006098664,"domain_scores_codex":[0.9989244,0.0003406783,0.0003895881,0.000169399,0.00005411427,0.0001217842],"domain_scores_gemma":[0.9983015,0.0007991919,0.0001197909,0.0005060704,0.0002510587,0.00002236632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006572859,0.0003739426,0.8673322,0.00007266142,0.0000566052,0.000001939597,0.001000052,0.0000440629,0.1148577,0.004304362,0.0091248,0.002765943],"study_design_scores_gemma":[0.003091556,0.00006939918,0.6767064,0.0002275607,0.00004896834,3.619364e-7,0.006730176,0.2227104,0.07237314,0.00179708,0.01593178,0.0003131293],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9695452,0.0002232199,0.02810054,0.0002776795,0.0001902997,0.0005040545,0.00005203173,0.0003104049,0.0007966009],"genre_scores_gemma":[0.9473902,0.00006479782,0.0513713,0.0004507689,0.00001705083,0.0001731066,0.0002503179,0.000008069162,0.0002744125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2226664,"threshold_uncertainty_score":0.3403198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1902915058139886,"score_gpt":0.436819814885397,"score_spread":0.2465283090714084,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}