{"id":"W2579534470","doi":"","title":"Training Data Enrichment for Infrequent Discourse Relations","year":2016,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parsing; Computer science; Training set; Relation (database); Natural language processing; Artificial intelligence; Training (meteorology); Confidence interval; Quality (philosophy); Machine learning; Data mining; Statistics","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":[0.009819563,0.001921571,0.001649217,0.002508579,0.001755386,0.001671356,0.002675527,0.003472533,0.003107717],"category_scores_gemma":[0.04363262,0.001035938,0.001568262,0.002113493,0.001382915,0.004070283,0.003579178,0.004153769,0.003210494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009477233,"about_ca_system_score_gemma":0.002176586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002563991,"about_ca_topic_score_gemma":0.005467535,"domain_scores_codex":[0.9920782,0.003442381,0.0006091158,0.002519438,0.0009441559,0.0004067457],"domain_scores_gemma":[0.9468291,0.03876746,0.00177678,0.007707406,0.004270123,0.0006490824],"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":[0.001506272,0.002378508,0.0494043,0.001073895,0.0002886457,0.001362294,0.002937096,0.05379548,0.06734043,0.006139383,0.02729565,0.786478],"study_design_scores_gemma":[0.0001582421,0.0005923553,0.009649676,0.0002388523,0.0002322437,0.0008444557,0.001198024,0.8404607,0.1054937,0.01479494,0.02623863,0.00009831866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3316331,0.001224178,0.6375189,0.001545961,0.0003439669,0.0007044203,0.002569364,0.01997371,0.004486403],"genre_scores_gemma":[0.4783269,0.0001930432,0.5049353,0.0006429923,0.00014967,0.0007217721,0.01042653,0.001070848,0.003532837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009819563,"threshold_uncertainty_score":0.05193144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1427233374709916,"score_gpt":0.4063764021825755,"score_spread":0.2636530647115839,"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."}}