{"id":"W194491081","doi":"10.82308/16076","title":"Crosslingual implementation of linguistic taggers using parallel corpora","year":2008,"lang":"en","type":"book","venue":"eScholarship@McGill (McGill)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Sentence; Set (abstract data type); Part of speech; Linguistics; Programming language","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":[0.004120294,0.001184539,0.001062272,0.003077521,0.001736681,0.004354763,0.002479925,0.001466244,0.0143636],"category_scores_gemma":[0.01100694,0.001723973,0.001581794,0.003251668,0.0009693654,0.007909001,0.004051274,0.001991909,0.01202565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00128728,"about_ca_system_score_gemma":0.002502048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007566269,"about_ca_topic_score_gemma":0.01177459,"domain_scores_codex":[0.9966789,0.0008311271,0.000483544,0.001087412,0.0007149879,0.0002039666],"domain_scores_gemma":[0.9934506,0.002100336,0.000274262,0.002464199,0.001542828,0.0001677464],"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":[0.0009457723,0.0008908957,0.007678552,0.001074904,0.0003828472,0.00144066,0.004078892,0.01442011,0.06861063,0.02304778,0.03758023,0.8398488],"study_design_scores_gemma":[0.0004933891,0.000582024,0.01237246,0.0003094231,0.0004705952,0.001838789,0.00433968,0.3522793,0.2548299,0.04598129,0.3260433,0.0004599221],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05458484,0.00053597,0.8132132,0.000457663,0.0009800404,0.0008613308,0.00476838,0.1022153,0.02238326],"genre_scores_gemma":[0.1462671,0.000448363,0.8109997,0.0003169971,0.0001169882,0.0008339798,0.0155247,0.008006182,0.01748605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0143636,"threshold_uncertainty_score":0.048051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02989624977126489,"score_gpt":0.2952183447783031,"score_spread":0.2653220950070382,"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."}}