{"id":"W2949495625","doi":"10.48550/arxiv.1302.6777","title":"Ending-based Strategies for Part-of-speech Tagging","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Word (group theory); Punctuation; Computer science; Part of speech; Natural language processing; Artificial intelligence; Part-of-speech tagging; Set (abstract data type); Word error rate; Speech recognition; Mathematics","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":[0.005273066,0.001404082,0.0009765215,0.002656875,0.0009178061,0.001796629,0.00187484,0.001321092,0.003483682],"category_scores_gemma":[0.01416263,0.0007727992,0.0009400151,0.00186338,0.001066611,0.00368216,0.002465805,0.00181331,0.008434398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003485563,"about_ca_system_score_gemma":0.0007865446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003301039,"about_ca_topic_score_gemma":0.001002509,"domain_scores_codex":[0.996529,0.001449449,0.000436359,0.000814285,0.0005883994,0.0001824568],"domain_scores_gemma":[0.9836162,0.0081004,0.0008818611,0.004603146,0.002503235,0.0002951995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009626666,0.0004212937,0.01454863,0.0006992657,0.0002336836,0.0008469358,0.001807027,0.04096735,0.1807151,0.03785898,0.007628218,0.7133109],"study_design_scores_gemma":[0.00008447823,0.0007888352,0.005340042,0.0001344038,0.0002117451,0.002170973,0.000521845,0.5624519,0.2703042,0.1205596,0.03714457,0.0002873838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02321832,0.000193683,0.9695386,0.00006494756,0.0001126492,0.00009833237,0.0003319799,0.004459007,0.001982425],"genre_scores_gemma":[0.2341145,0.0002081358,0.7575959,0.0001819938,0.00008613633,0.0002800076,0.001875571,0.00180657,0.003851179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005273066,"threshold_uncertainty_score":0.02788693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07083707437817484,"score_gpt":0.221181173725023,"score_spread":0.1503440993468482,"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."}}