{"id":"W4231122779","doi":"10.18653/v1/2021.emnlp-main.288","title":"Automated Generation of Accurate & Fluent Medical X-ray Reports","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Fluency; Embedding; Generator (circuit theory); Transformer; Natural language processing; Artificial intelligence; Information retrieval; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.002099289,0.000210727,0.0004511312,0.0001406998,0.0000854824,0.0001536536,0.0009055932,0.0001951491,0.0000552703],"category_scores_gemma":[0.006296829,0.0001474508,0.0001156545,0.001190049,0.0001044897,0.0004301162,0.0006095886,0.0006226657,7.792056e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007274555,"about_ca_system_score_gemma":0.000476146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001734417,"about_ca_topic_score_gemma":0.00001060311,"domain_scores_codex":[0.9970958,0.0001773294,0.0008771544,0.0006425262,0.0008973333,0.000309829],"domain_scores_gemma":[0.997941,0.0001981262,0.0006099169,0.0003536959,0.0008021703,0.00009508977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001549944,0.0001884237,0.001650784,0.0003719779,0.00002634293,0.00004410133,0.005228139,0.0002207124,0.5184672,0.003524655,0.0001438938,0.4701182],"study_design_scores_gemma":[0.0002089572,0.00001917606,0.0008382465,0.0007299479,0.00001330646,0.00007523274,0.0003159424,0.7957698,0.1997274,0.002016811,0.00007821244,0.0002070109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6914437,0.004686092,0.2891923,0.009736587,0.001388772,0.0004262011,0.000001946038,0.0002790397,0.002845421],"genre_scores_gemma":[0.5906454,0.00001305685,0.4089021,0.0002539236,0.00006156299,0.000008629899,0.000001246828,0.000007533083,0.0001065019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.795549,"threshold_uncertainty_score":0.7538347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09840819144765348,"score_gpt":0.4311545131288209,"score_spread":0.3327463216811675,"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."}}