{"id":"W2807399664","doi":"10.63317/5894atgjvr8a","title":"SPADE: Evaluation Dataset for Monolingual Phrase Alignment","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Computer science; Phrase; Natural language processing; Artificial intelligence; Speech recognition; Information retrieval","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":[0.003849793,0.005257766,0.002608526,0.007280873,0.003107472,0.002331433,0.005950417,0.003970614,0.0251888],"category_scores_gemma":[0.01110894,0.001225573,0.002421997,0.005943472,0.001139479,0.004811015,0.005957276,0.003247516,0.04060262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001606674,"about_ca_system_score_gemma":0.00546275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02105367,"about_ca_topic_score_gemma":0.05229866,"domain_scores_codex":[0.9946132,0.00128407,0.0007525787,0.00146606,0.001358821,0.0005253265],"domain_scores_gemma":[0.9923106,0.001762575,0.0004090149,0.002178452,0.002485574,0.0008537743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001098545,0.0009853512,0.003210681,0.002142464,0.0004349612,0.0004315365,0.0002256928,0.002196588,0.009361541,0.001876419,0.8992683,0.07876789],"study_design_scores_gemma":[0.00433072,0.001540844,0.02921108,0.0008326345,0.000898922,0.003037835,0.001794608,0.05380692,0.04126592,0.008600393,0.85416,0.0005200555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04952542,0.002780194,0.02014691,0.0009385124,0.001402554,0.001492721,0.8553248,0.05007637,0.01831256],"genre_scores_gemma":[0.007161469,0.0001819955,0.01476824,0.0001750192,0.0000553273,0.0004432624,0.9735411,0.0007403039,0.00293324],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0251888,"threshold_uncertainty_score":0.08426493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04295690952217326,"score_gpt":0.3728724622383085,"score_spread":0.3299155527161353,"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."}}