{"id":"W4316135769","doi":"10.48550/arxiv.2301.05220","title":"Adversarial Adaptation for French Named Entity Recognition","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Mitacs","keywords":"Overfitting; Computer science; Named-entity recognition; Domain adaptation; Transformer; Adversarial system; Artificial intelligence; Natural language processing; Machine learning; Adaptation (eye); Task (project management); Labeled data; Artificial neural network; Classifier (UML)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001855604,0.0009323041,0.000701324,0.0005597411,0.0003584389,0.0005799679,0.001035784,0.0008103538,0.001739183],"category_scores_gemma":[0.004621748,0.0003196141,0.0006892646,0.0006719159,0.0008778919,0.001049681,0.001174338,0.001546698,0.0008777505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008665951,"about_ca_system_score_gemma":0.000417236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006020099,"about_ca_topic_score_gemma":0.005423038,"domain_scores_codex":[0.9991948,0.0003765071,0.00002662186,0.0002302488,0.0001023466,0.00006941525],"domain_scores_gemma":[0.9979321,0.001419733,0.0001167598,0.0003129479,0.0001749312,0.00004372837],"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":[0.000115261,0.00004340156,0.0008603124,0.00003654429,0.00005858856,0.0001283293,0.00008710709,0.9194502,0.002747923,0.01076989,0.004919369,0.06078309],"study_design_scores_gemma":[0.000002302653,0.000006358356,0.0001215841,0.000002358041,0.000003183724,0.00001310504,0.000004654632,0.9955425,0.0005527139,0.003248629,0.0004983803,0.000004276687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03852586,0.0005276024,0.9546803,0.0004859712,0.00009428436,0.0000594016,0.0003822779,0.001884607,0.003359611],"genre_scores_gemma":[0.871887,0.0004861418,0.114739,0.0005061408,0.0001277179,0.0001982537,0.002139558,0.0003135775,0.009602663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006020099,"threshold_uncertainty_score":0.0119701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2201451309572046,"score_gpt":0.2070984495315644,"score_spread":0.01304668142564022,"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."}}