{"id":"W2400453854","doi":"","title":"Learning Transformation Rules for Semantic Role Labeling","year":2004,"lang":"en","type":"article","venue":"Conference on Computational Natural Language Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Novelty; Brill; Transformation (genetics); Computer science; Semantic role labeling; Natural language processing; Artificial intelligence; Verb; Information retrieval; Philosophy; Chemistry","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":[0.0003536292,0.0002514101,0.0002299885,0.0002531343,0.0004978592,0.0004292122,0.0006091752,0.0001136367,0.00001123262],"category_scores_gemma":[0.0003418436,0.0002306614,0.0001089946,0.0003028123,0.00004229199,0.0008003333,0.00008084156,0.000814139,0.00004877172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001170425,"about_ca_system_score_gemma":0.0001424921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003290554,"about_ca_topic_score_gemma":0.000005833619,"domain_scores_codex":[0.9983205,0.000090858,0.0003147131,0.0004529899,0.000441764,0.00037924],"domain_scores_gemma":[0.9989588,0.0002782621,0.000197435,0.0001511302,0.0003369154,0.00007742573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004277648,0.00004834605,0.00003019375,0.0000978035,0.00002963618,0.00002084697,0.0102102,0.1393132,0.01034507,0.5544293,0.00000906224,0.2854236],"study_design_scores_gemma":[0.001141741,0.0003559473,0.0001170407,0.0003749041,0.00001386699,0.0000488615,0.001099265,0.83319,0.008970433,0.1539316,0.0002132675,0.0005430458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05995464,0.001786713,0.9343405,0.001645429,0.0001737502,0.0003520713,0.000003272547,0.00123096,0.0005126867],"genre_scores_gemma":[0.6894603,0.000005795273,0.3099478,0.0002295575,0.0000675533,0.00002271766,0.0001280864,0.00001614267,0.0001220082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6938768,"threshold_uncertainty_score":0.9406098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01167356504857882,"score_gpt":0.2795745289702728,"score_spread":0.267900963921694,"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."}}