{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00216786,0.0003928923,0.0005089827,0.0004072031,0.000313713,0.0005875306,0.00153366,0.0003363698,0.000014883],"category_scores_gemma":[0.002845242,0.000329358,0.000193395,0.001083719,0.0001619848,0.001271519,0.0003930228,0.001598802,0.000002843995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009413638,"about_ca_system_score_gemma":0.0001674274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003961436,"about_ca_topic_score_gemma":0.0000646707,"domain_scores_codex":[0.9968623,0.0002941127,0.0006564897,0.00095568,0.0003851508,0.0008462884],"domain_scores_gemma":[0.997816,0.0009231498,0.0002824934,0.0005786067,0.000233857,0.0001659339],"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":[0.00002727172,0.00004956289,0.0002187799,0.0001057461,0.000005567016,0.00003545203,0.002102491,4.562685e-7,0.1366746,0.002110929,0.00008523027,0.8585839],"study_design_scores_gemma":[0.002276807,0.0001603762,0.0005568934,0.000752644,0.00005145219,0.0004415581,0.001690784,0.4262227,0.4972451,0.06125576,0.00730732,0.00203869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01091721,0.03161757,0.953011,0.001395889,0.001335166,0.0005003957,0.000002627256,0.0009325986,0.0002875288],"genre_scores_gemma":[0.4470566,0.0000022803,0.5517959,0.0008094808,0.0001932852,0.00004418857,0.000003827702,0.00002604343,0.00006844875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8565452,"threshold_uncertainty_score":0.9999158,"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."}}