{"id":"W3037085112","doi":"10.18653/v1/2020.repl4nlp-1.23","title":"Supertagging with CCG primitives","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Lexicalization; Computer science; Natural language processing; Artificial intelligence; Parsing; Word (group theory); Part of speech; Rule-based machine translation; Task (project management); Sentence; Linguistics","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":[0.00003410009,0.00006520739,0.00006452844,0.00002021147,0.00004066584,0.0001134612,0.0004931577,0.00001790278,0.00001500244],"category_scores_gemma":[0.00002651782,0.0000417242,0.00001285779,0.0002241411,0.00001977719,0.0004594523,0.0001372848,0.0000809873,0.0000148031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006709736,"about_ca_system_score_gemma":0.00002646166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007583141,"about_ca_topic_score_gemma":0.000001307549,"domain_scores_codex":[0.9994888,0.00001071436,0.0000540578,0.0002066733,0.0001223908,0.0001173262],"domain_scores_gemma":[0.9997267,0.00002113204,0.00001674056,0.0001403582,0.0000340301,0.00006102983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001942691,0.00003993858,0.002249007,0.00006667564,0.00002382165,0.0001749953,0.006557704,0.000005048566,0.02881466,0.7852215,0.003911789,0.1729155],"study_design_scores_gemma":[0.0005226731,0.0005235405,0.0005010515,0.00009940053,0.000008347739,0.00005210324,0.0002191993,0.04977075,0.9219533,0.01746287,0.00812029,0.0007665096],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001905705,0.0003000451,0.9824395,0.008937081,0.00001059219,0.00005407605,1.237647e-7,0.001380382,0.004972466],"genre_scores_gemma":[0.475029,0.000001151212,0.52224,0.002644466,0.00001586104,0.000001975302,1.929203e-7,0.000002947105,0.00006436391],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8931386,"threshold_uncertainty_score":0.1701463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393717394215412,"score_gpt":0.2319330178308518,"score_spread":0.2179958438886976,"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."}}