{"id":"W1569397218","doi":"","title":"Utilizing Extra-Sentential Context for Parsing","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Treebank; Parsing; Computer science; Natural language processing; Artificial intelligence; Context (archaeology); Consistency (knowledge bases); Conditional random field; Generative grammar; Set (abstract data type); Feature (linguistics); Linguistics; Programming language","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":[0.003607569,0.001010597,0.0008795559,0.002387814,0.001252411,0.002524212,0.001193983,0.001174558,0.00295625],"category_scores_gemma":[0.01647549,0.001010086,0.0008056748,0.002118652,0.00110727,0.005743702,0.002036297,0.002147874,0.001127572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009030251,"about_ca_system_score_gemma":0.001999156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004363167,"about_ca_topic_score_gemma":0.01346379,"domain_scores_codex":[0.9971641,0.001287888,0.0001470554,0.0007259041,0.0005401171,0.0001349242],"domain_scores_gemma":[0.9904132,0.005982772,0.0005411411,0.002054213,0.0008802782,0.0001283804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007121082,0.0004203663,0.03085073,0.0006706361,0.000303706,0.001092777,0.002179008,0.1051839,0.0733434,0.06751309,0.01710697,0.7006233],"study_design_scores_gemma":[0.00007630782,0.0001627264,0.01305886,0.0001019088,0.0003014199,0.000717827,0.0003410002,0.7841001,0.05567835,0.1249592,0.02026481,0.0002375091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2088213,0.0008720917,0.769417,0.0009804724,0.0001410972,0.000173587,0.001862617,0.0102099,0.007521971],"genre_scores_gemma":[0.7508827,0.0002648342,0.2439507,0.0001828699,0.00008836942,0.00009096759,0.001984204,0.001145414,0.001409975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004363167,"threshold_uncertainty_score":0.01907891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05448447238682705,"score_gpt":0.4465676489612256,"score_spread":0.3920831765743986,"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."}}