{"id":"W2096446497","doi":"10.3115/v1/w14-2405","title":"A Deep Architecture for Semantic Parsing","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Canadian Institute for Advanced Research; Xerox Foundation","keywords":"Computer science; Natural language processing; Parsing; Artificial intelligence; Ontology; Semantics (computer science); Bottom-up parsing; Architecture; Natural language; Top-down parsing; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001810567,0.00007254048,0.00008216344,0.00005751014,0.00007466951,0.0001211715,0.0005305539,0.00003850573,0.000002842146],"category_scores_gemma":[0.0001037206,0.00005319765,0.00003808694,0.0001265262,0.00001496409,0.0001359691,0.0000969523,0.00006992101,0.000004879822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009646385,"about_ca_system_score_gemma":0.000009736216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006892896,"about_ca_topic_score_gemma":0.00001282152,"domain_scores_codex":[0.9994257,0.00001888594,0.00008114012,0.0002063925,0.00009030345,0.0001775946],"domain_scores_gemma":[0.9995043,0.0001053874,0.00003048717,0.0002835248,0.0000398859,0.00003636853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002903912,0.00001200319,0.00002088844,0.00004540537,0.000003669665,0.000001111755,0.0003271282,0.00002191314,0.003585983,0.3253053,0.0007722906,0.6699014],"study_design_scores_gemma":[0.0001347996,0.00007111709,0.00001444865,0.00003116632,0.000003486888,0.00002488329,0.000003465956,0.3220523,0.03579045,0.6355679,0.006138086,0.000167927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002128879,0.0002360062,0.9959272,0.001805767,0.00007182933,0.0001139171,7.373103e-8,0.0007515281,0.00088083],"genre_scores_gemma":[0.3064767,3.080024e-7,0.6925573,0.0008042087,0.00004153791,0.000009048972,4.433255e-7,0.000004360032,0.0001061529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6697335,"threshold_uncertainty_score":0.2169337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008633571998138169,"score_gpt":0.2575819397505558,"score_spread":0.2489483677524177,"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."}}