{"id":"W2252267789","doi":"10.3115/v1/p14-1048","title":"A Linear-Time Bottom-Up Discourse Parser with Constraints and Post-Editing","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Pennsylvania","keywords":"Computer science; Top-down and bottom-up design; Parsing; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000261564,0.0001261384,0.0001311815,0.00005350106,0.00008591256,0.0001711907,0.0003728188,0.0000516791,0.00003349066],"category_scores_gemma":[0.00009620492,0.00008231473,0.00001667716,0.0001331614,0.000193662,0.0005043712,0.0001767327,0.0001635331,0.00002120268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008349915,"about_ca_system_score_gemma":0.00003363824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000248824,"about_ca_topic_score_gemma":0.000008013844,"domain_scores_codex":[0.9991397,0.00003560571,0.0001141607,0.0003076038,0.0001807022,0.0002222734],"domain_scores_gemma":[0.9993884,0.00007898522,0.00006463171,0.0002788777,0.0001007477,0.00008839067],"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":[0.00002432292,0.00007539242,0.002253793,0.00007551001,0.00004098865,0.00007164701,0.001662866,0.000001893133,0.02498705,0.2098045,0.00209193,0.7589101],"study_design_scores_gemma":[0.005176472,0.002797072,0.003696591,0.001569363,0.0001351438,0.002770768,0.001044393,0.5773008,0.3049015,0.09273114,0.003628592,0.004248121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05169041,0.0001252549,0.9414883,0.002695024,0.00007051182,0.0001447524,0.000001995121,0.0009836828,0.002800015],"genre_scores_gemma":[0.5134591,5.830897e-7,0.4853093,0.0006121174,0.00005086625,0.000003737231,0.000001323717,0.000006088101,0.0005568324],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.754662,"threshold_uncertainty_score":0.3356697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006619083121696493,"score_gpt":0.2536527261051099,"score_spread":0.2470336429834134,"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."}}