{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001622251,0.001348632,0.001686735,0.0006906533,0.001012291,0.002200913,0.002975174,0.001873112,0.008187864],"category_scores_gemma":[0.005734541,0.001163999,0.00125509,0.001119082,0.0007363296,0.004812293,0.001280844,0.00322777,0.008325867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000906244,"about_ca_system_score_gemma":0.003741825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005570561,"about_ca_topic_score_gemma":0.01186867,"domain_scores_codex":[0.9989443,0.0002849986,0.00007805104,0.0003836952,0.0002140318,0.00009503925],"domain_scores_gemma":[0.9953458,0.002728277,0.000180197,0.001068267,0.0005754073,0.0001020603],"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":[0.0003572341,0.0002704397,0.001757206,0.000945,0.0001601553,0.0006374493,0.0006110719,0.09852849,0.06103119,0.02817047,0.04508465,0.7624466],"study_design_scores_gemma":[0.00004126442,0.00007147738,0.0005323785,0.00005034129,0.0001002824,0.0003819785,0.0001295712,0.9112642,0.03709122,0.02811832,0.0221564,0.00006258124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009644452,0.000363847,0.9609017,0.0005694328,0.0001146964,0.0001138519,0.0007723237,0.02515183,0.00236793],"genre_scores_gemma":[0.1703621,0.0003933248,0.8162329,0.0003425311,0.0001190906,0.0001505488,0.002691679,0.002245965,0.007461896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008187864,"threshold_uncertainty_score":0.02739114,"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."}}