{"id":"W4293863204","doi":"10.1109/siu55565.2022.9864782","title":"Annotation of Financial Entities Using A Comprehensive Scheme in Turkish","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Turkish; Natural language processing; Annotation; Artificial intelligence; Information extraction; Task (project management); Scarcity; Named-entity recognition; Baseline (sea); Language model; Quality (philosophy); Distributional semantics; Domain (mathematical analysis); Stock market; Information retrieval; Context (archaeology); Semantic similarity; 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":[0.002145534,0.0001693745,0.000360241,0.0006071199,0.001295037,0.0001978373,0.00160834,0.00005936933,0.0002403125],"category_scores_gemma":[0.00038999,0.0001812769,0.00006361369,0.002493609,0.0005253485,0.0003143089,0.001117273,0.0004972699,0.000003230091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009254778,"about_ca_system_score_gemma":0.0006666542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001505819,"about_ca_topic_score_gemma":0.00005773656,"domain_scores_codex":[0.9968003,0.0008170833,0.0009181008,0.0004708196,0.0007630909,0.0002306099],"domain_scores_gemma":[0.9958528,0.001402723,0.0007079674,0.001112423,0.0008563958,0.00006770037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009121952,0.000498202,0.01602799,0.00008015419,0.00001672657,0.00000105371,0.005627912,0.001881631,0.01772397,0.04388215,0.0002970906,0.9138719],"study_design_scores_gemma":[0.001110458,0.0001685928,0.03452348,0.0001467262,0.0000611513,0.00005414576,0.02301908,0.7338338,0.0005524529,0.1613928,0.04443346,0.0007038722],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6578962,0.005791137,0.3261343,0.001383461,0.0000820261,0.001517888,0.0002156547,0.0001179465,0.006861404],"genre_scores_gemma":[0.9374672,0.0000605157,0.0614197,0.00009804819,0.00001869088,0.0006730693,0.00004275508,0.00001348866,0.0002065698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.913168,"threshold_uncertainty_score":0.9960511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1945697109168684,"score_gpt":0.412816230078733,"score_spread":0.2182465191618646,"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."}}