{"id":"W4400770852","doi":"10.1109/tcss.2024.3421672","title":"<i>XeroPol</i>: Emotion-Aware Contrastive Learning for Zero-Shot Cross-Lingual Politeness Identification in Dialogues","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Social Systems","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Politeness; Identification (biology); Zero (linguistics); Natural language processing; Computer science; Speech recognition; Linguistics; Artificial intelligence; Contrastive analysis; Psychology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001114137,0.0002010043,0.0003134786,0.0002890478,0.002492412,0.0001463979,0.0001974854,0.0003185321,0.00003662592],"category_scores_gemma":[0.00006659134,0.000216741,0.0001676104,0.0004205015,0.0001130101,0.0001926915,0.000003160297,0.0009605676,0.0001441781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007467052,"about_ca_system_score_gemma":0.0005377065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001791493,"about_ca_topic_score_gemma":0.0001627302,"domain_scores_codex":[0.996681,0.001086347,0.001044107,0.0004081794,0.0003584036,0.0004219238],"domain_scores_gemma":[0.9958078,0.002985385,0.0002358855,0.0001345254,0.0007560901,0.00008031555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005913231,0.0003765266,0.003670922,0.003384786,0.0002858335,0.000006642351,0.08346891,0.8467783,0.0002401345,0.04398036,0.001276457,0.01593982],"study_design_scores_gemma":[0.002799172,0.0003598887,0.01892539,0.00418799,0.0001161589,0.00001307062,0.03770489,0.9141061,0.0001691003,0.01339732,0.007180715,0.001040236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1008953,0.0002454931,0.8881444,0.001105578,0.006602982,0.001594378,0.0004503956,0.0004327004,0.0005288627],"genre_scores_gemma":[0.9960839,0.00001626124,0.00007799984,0.0001525528,0.0006497501,0.001309411,0.0002886096,0.00005252092,0.001369049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8951886,"threshold_uncertainty_score":0.9988062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010558838363001,"score_gpt":0.4607011190128147,"score_spread":0.3596452351765145,"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."}}