{"id":"W4403941104","doi":"10.1007/978-981-97-9443-0_15","title":"Overview of the NLPCC 2024 Shared Task on Chinese Metaphor Generation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Metaphor; Task (project management); Linguistics; Systems engineering; Philosophy; Engineering","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":[0.002028023,0.002763863,0.001825062,0.001830433,0.00182691,0.002942635,0.002951497,0.002029026,0.09396508],"category_scores_gemma":[0.004278168,0.0009969842,0.0009517259,0.003123914,0.000722553,0.004694349,0.004475708,0.00204462,0.04371873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468402,"about_ca_system_score_gemma":0.00409014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01249472,"about_ca_topic_score_gemma":0.01067737,"domain_scores_codex":[0.9985698,0.0004070659,0.0001302825,0.0003909545,0.0003358888,0.0001659465],"domain_scores_gemma":[0.9984888,0.0005154497,0.00003694105,0.0003781876,0.0003781548,0.0002025032],"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":[0.0008685475,0.0005233231,0.000878722,0.001926986,0.00007685558,0.000376798,0.001082011,0.003198996,0.0423601,0.01677927,0.1845272,0.7474012],"study_design_scores_gemma":[0.0007155648,0.0008320149,0.01064842,0.0004588934,0.0001525469,0.001723825,0.001297624,0.0737545,0.07187489,0.07339527,0.7647465,0.0003999871],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.03923243,0.007916669,0.5589414,0.002427156,0.001525789,0.007862898,0.0507223,0.05531969,0.2760517],"genre_scores_gemma":[0.1688265,0.002771121,0.5730457,0.001313825,0.000621353,0.0139982,0.1464648,0.008465327,0.08449316],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09396508,"threshold_uncertainty_score":0.3143445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03720169001192833,"score_gpt":0.310405091491613,"score_spread":0.2732034014796847,"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."}}