{"id":"W4414231430","doi":"10.1109/amlds63918.2025.11159378","title":"Error Analysis for POS Tagging of Hindi-English Code-Mixed Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sentence; Noun; Task (project management); Hindi; Spelling; Word (group theory); Error detection and correction; Error analysis","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":[0.01124219,0.0006581835,0.0005060842,0.00319374,0.001244584,0.0013519,0.0008952479,0.0009825957,0.00102572],"category_scores_gemma":[0.05368399,0.0002690546,0.0006562249,0.003277111,0.001133969,0.001192031,0.00131534,0.001113719,0.0008827636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187572,"about_ca_system_score_gemma":0.0009390554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00519185,"about_ca_topic_score_gemma":0.005588025,"domain_scores_codex":[0.9889065,0.004352518,0.001733004,0.002133774,0.002511435,0.0003627225],"domain_scores_gemma":[0.8924094,0.07524398,0.007243545,0.01004905,0.01430836,0.0007455573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005589576,0.0006972827,0.4554346,0.001900762,0.000845881,0.005753664,0.008714879,0.04755094,0.05961104,0.008929946,0.01607252,0.3888989],"study_design_scores_gemma":[0.0001469849,0.0006976384,0.2782269,0.0003308441,0.0004099492,0.004511384,0.003451649,0.499773,0.1648202,0.01566332,0.03167305,0.000295051],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8622202,0.0007015524,0.1247848,0.0004272571,0.0005368539,0.0002729374,0.006174012,0.002519662,0.002362819],"genre_scores_gemma":[0.9116253,0.0001148873,0.07242899,0.0002141566,0.00005348216,0.0002189508,0.01317833,0.0004604683,0.001705476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01124219,"threshold_uncertainty_score":0.05945504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519192064712283,"score_gpt":0.3393133186949903,"score_spread":0.3041213980478674,"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."}}