{"id":"W3150672550","doi":"10.1007/978-3-030-72113-8_21","title":"An Argument Extraction Decoder in Open Information Extraction","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Predicate (mathematical logic); Argument (complex analysis); Information extraction; Artificial intelligence; Sentence; Natural language processing; Algorithm; Theoretical computer science; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001692362,0.001086976,0.001351085,0.002354512,0.001105977,0.003356015,0.002047398,0.002204191,0.02660576],"category_scores_gemma":[0.007332091,0.00120398,0.001173727,0.002409055,0.001063861,0.005820575,0.004313756,0.002316078,0.0175292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007797517,"about_ca_system_score_gemma":0.00166359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009469115,"about_ca_topic_score_gemma":0.001889271,"domain_scores_codex":[0.9987119,0.0003159629,0.000174673,0.0002634389,0.0004458249,0.0000881962],"domain_scores_gemma":[0.9957736,0.002326796,0.000112447,0.0008499065,0.0008549255,0.00008234627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003827627,0.0001358052,0.0005831693,0.0005502959,0.00005933313,0.0004992124,0.0004277481,0.003583227,0.01512299,0.1336025,0.061227,0.7838259],"study_design_scores_gemma":[0.0001538469,0.0001096977,0.0005006126,0.0003534018,0.0001963329,0.001134215,0.0003011255,0.2668026,0.122835,0.3637032,0.2437974,0.0001127345],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003117133,0.0003580381,0.9622306,0.0004305152,0.0003095685,0.0001360414,0.001234175,0.02177822,0.01040575],"genre_scores_gemma":[0.06373523,0.0004495175,0.9012164,0.0005219815,0.0002553328,0.0002257384,0.00426101,0.005206434,0.02412829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02660576,"threshold_uncertainty_score":0.08900511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01703601336802922,"score_gpt":0.3120898653853281,"score_spread":0.2950538520172989,"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."}}