{"id":"W2986463783","doi":"10.16995/dm.83","title":"Data-Driven Syllabification for Middle Dutch","year":2019,"lang":"en","type":"article","venue":"Digital Medievalist","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Computer science; Speech recognition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001784141,0.0001116021,0.0001325159,0.0000583565,0.00004688062,0.0005069135,0.001936106,0.00005720314,0.000006088856],"category_scores_gemma":[0.0002953811,0.00009533793,0.00003485064,0.0002025431,0.00003277155,0.001927507,0.0004594857,0.00007571506,0.0001176408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000371645,"about_ca_system_score_gemma":0.00004984681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004292429,"about_ca_topic_score_gemma":0.000002773789,"domain_scores_codex":[0.9988801,0.000009581073,0.000179133,0.0004687235,0.0002553479,0.0002070941],"domain_scores_gemma":[0.9983971,0.0001263761,0.00009470146,0.001181665,0.0001377013,0.0000624325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006650577,0.000315731,0.002156951,0.000740435,0.00008022886,0.00001850729,0.001349596,0.00001116762,0.01045917,0.4202962,0.04490976,0.5195957],"study_design_scores_gemma":[0.001761805,0.0005717944,0.000395143,0.0004832654,0.00003906213,0.00008483227,0.0002014543,0.2918816,0.02844066,0.1799115,0.4945114,0.001717434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009164162,0.00146243,0.9717382,0.003222366,0.00120192,0.001207154,0.0005809084,0.001714418,0.009708449],"genre_scores_gemma":[0.7174521,0.000004544984,0.2797907,0.000320726,0.0001380328,0.00003293963,0.0006143306,0.00001919117,0.001627478],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.708288,"threshold_uncertainty_score":0.4888179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04931733786985358,"score_gpt":0.3019499079354149,"score_spread":0.2526325700655613,"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."}}