{"id":"W7096948591","doi":"","title":"Abstract Estimating Upper and Lower Bounds on the Performance of Word-Sense Disambiguation Programs","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Upper and lower bounds; Context (archaeology); Measure (data warehouse); Baseline (sea); Word-sense disambiguation","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.02689702,0.002445795,0.002677924,0.006774405,0.001579329,0.00557878,0.002503077,0.004030267,0.002735472],"category_scores_gemma":[0.1657982,0.001481013,0.001257453,0.003765101,0.002919815,0.007305755,0.004198711,0.003045719,0.00184466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003478527,"about_ca_system_score_gemma":0.001559753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007975372,"about_ca_topic_score_gemma":0.005068782,"domain_scores_codex":[0.9542898,0.01604581,0.002857977,0.01023857,0.0136657,0.002902149],"domain_scores_gemma":[0.7059963,0.255074,0.008217007,0.01344541,0.01510275,0.002164577],"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":[0.007814916,0.0008986976,0.06123678,0.00204349,0.001295099,0.0006917863,0.00172911,0.4391451,0.04561315,0.02216148,0.01578397,0.4015864],"study_design_scores_gemma":[0.00008381767,0.0008170907,0.02543033,0.0002260694,0.000181834,0.0003370258,0.0004666727,0.8978152,0.05199714,0.01962584,0.002829868,0.0001890875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5646531,0.0137027,0.3908161,0.001787304,0.0002909678,0.0002480074,0.002838698,0.007277367,0.01838582],"genre_scores_gemma":[0.8943008,0.0008357389,0.09756035,0.0002573112,0.0002663932,0.0003119315,0.003508709,0.0008902123,0.002068629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02689702,"threshold_uncertainty_score":0.1422468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02063433429826272,"score_gpt":0.2600485199419613,"score_spread":0.2394141856436986,"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."}}