{"id":"W2511646563","doi":"10.18653/v1/p16-1108","title":"Leveraging Inflection Tables for Stemming and Lemmatization.","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Lemmatisation; Inflection; Computer science; Artificial intelligence; Discriminative model; Natural language processing; String (physics); Task (project management); Exploit; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001152277,0.00003396684,0.00003770502,0.00003743397,0.00007476552,0.00006604434,0.00008543511,0.00001383229,0.000006383227],"category_scores_gemma":[0.00003051372,0.00002252137,0.000007733783,0.00004798579,0.000004571767,0.0004457218,0.00004753192,0.000008505923,0.00000189692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001515298,"about_ca_system_score_gemma":0.00001158684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001507053,"about_ca_topic_score_gemma":0.000006916043,"domain_scores_codex":[0.9996475,0.000006772673,0.00007830307,0.0001350917,0.0000488712,0.00008346292],"domain_scores_gemma":[0.9997495,0.00007158772,0.00002138412,0.0001051589,0.00003326586,0.00001903918],"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":[0.000001584711,0.000005594052,0.003525916,0.00002973385,0.0000076047,2.541924e-7,0.0007605249,0.0005078723,0.02264055,0.3399019,0.0004735825,0.6321449],"study_design_scores_gemma":[0.0006798664,0.00003082184,0.0006194912,0.0000750687,0.000003431352,0.000008158612,0.00006223076,0.9152457,0.03183832,0.03410598,0.01712645,0.0002045618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0216244,0.00002233692,0.9764826,0.001074338,0.0001072507,0.00007245575,1.743289e-7,0.00007839831,0.0005380247],"genre_scores_gemma":[0.7816347,0.000003327068,0.2170361,0.000100249,0.00003959384,0.000009307052,1.532458e-7,0.000002501804,0.001174032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9147378,"threshold_uncertainty_score":0.09183948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03247729577101645,"score_gpt":0.2436617284101015,"score_spread":0.2111844326390851,"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."}}