{"id":"W4405634912","doi":"10.1145/3623505","title":"AAC with Automated Vocabulary from Photographs: Insights from School and Speech-Language Therapy Settings","year":2024,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Assistive Technology in Communication and Mobility","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Vocabulary; Natural language processing; Artificial intelligence; Linguistics; Speech recognition","routes":{"ca_aff":true,"ca_fund":false,"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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003791937,0.0001600212,0.0002514188,0.0001152348,0.0008511824,0.00001916448,0.009870655,0.0002214314,0.0001343707],"category_scores_gemma":[0.002520251,0.0001023355,0.00007033,0.0005151358,0.0008653697,0.0001152968,0.009022934,0.00113869,0.00005790168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000747435,"about_ca_system_score_gemma":0.0002289815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002448012,"about_ca_topic_score_gemma":0.0009861967,"domain_scores_codex":[0.9980391,0.0009605833,0.000417259,0.0002651021,0.0001438233,0.0001741483],"domain_scores_gemma":[0.9732699,0.002143075,0.0002208349,0.02415192,0.0001438648,0.00007045412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003983067,0.001166014,0.6236469,0.0002559573,0.002288493,0.000008043441,0.04783939,0.000002800267,0.1036541,0.009421043,0.1850247,0.02629429],"study_design_scores_gemma":[0.0017115,0.0001014342,0.8116577,0.00217376,0.0002147226,0.000003399123,0.01990859,0.003621337,0.005917757,0.08794205,0.0662896,0.0004581564],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9357274,0.02838878,0.00002994848,0.02872583,0.0001229992,0.0009081714,0.0001854754,0.001072602,0.004838844],"genre_scores_gemma":[0.9512252,0.002143052,0.0451126,0.0009802748,0.00002024531,0.0002121192,0.0001403444,0.00002724215,0.0001388956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1880108,"threshold_uncertainty_score":0.9989919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04484317035672611,"score_gpt":0.3971932219695857,"score_spread":0.3523500516128596,"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."}}