{"id":"W2790100769","doi":"10.3389/fpsyg.2017.02335","title":"Using Neural Networks to Generate Inferential Roles for Natural Language","year":2018,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canada Research Chairs","keywords":"Computer science; Natural language processing; Syntax; Sentence; Semantics (computer science); Artificial intelligence; Set (abstract data type); Inference; Linguistics; Expression (computer science); Representation (politics); Logical consequence; Natural 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":[0.002072813,0.0009871866,0.0003132002,0.00113163,0.0004767279,0.001045669,0.001511685,0.0009868696,0.002623484],"category_scores_gemma":[0.0123829,0.0004325948,0.0008043618,0.0006114831,0.0008440724,0.003037079,0.001005291,0.002123048,0.0006059353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001657594,"about_ca_system_score_gemma":0.0006638802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003989901,"about_ca_topic_score_gemma":0.009349255,"domain_scores_codex":[0.9991975,0.0003799539,0.00004245479,0.0002097947,0.0001314167,0.00003891337],"domain_scores_gemma":[0.9951609,0.003883723,0.0002222113,0.0004127179,0.0002512807,0.00006924738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005241666,0.0004551771,0.00822293,0.0004534795,0.0002004228,0.0005518129,0.0009456816,0.5936463,0.01220334,0.08734429,0.01298028,0.2824721],"study_design_scores_gemma":[0.00001376137,0.00001493672,0.0002598148,0.00001420465,0.000008376597,0.00002120792,0.00002598078,0.9619974,0.001672918,0.03517812,0.0007879069,0.000005325911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2304608,0.0006974292,0.7507942,0.002391964,0.0001565365,0.0002729215,0.002147683,0.004296056,0.008782341],"genre_scores_gemma":[0.7227266,0.0002739575,0.2694361,0.0003383123,0.00006919843,0.0002825767,0.004068804,0.0002241538,0.002580248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003989901,"threshold_uncertainty_score":0.01202673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01985801118140234,"score_gpt":0.3481746268889014,"score_spread":0.328316615707499,"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."}}