{"id":"W2798416089","doi":"10.18653/v1/p18-1224","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":276,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Queen's University","funders":"","keywords":"Computer science; Inference; Leverage (statistics); Artificial intelligence; Artificial neural network; Natural language; Machine learning; Task (project management); Language model; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.00007631073,0.0001184523,0.00010299,0.00005140685,0.00007413475,0.0001233214,0.000753187,0.00002968938,0.00003736059],"category_scores_gemma":[0.00001076356,0.00008256398,0.00002426572,0.0001675443,0.00005348665,0.0007289691,0.0002501717,0.0001260569,0.00008295733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000207202,"about_ca_system_score_gemma":0.00005281968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007029304,"about_ca_topic_score_gemma":0.0001850453,"domain_scores_codex":[0.9990736,0.00002563251,0.0001237365,0.0003412144,0.0001712429,0.0002645843],"domain_scores_gemma":[0.9992458,0.0000368912,0.00003549587,0.0004938583,0.0001163965,0.00007157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004093754,0.0001116945,0.0002994691,0.00002583836,0.00002599795,0.00004117479,0.01986011,0.002719226,0.04143073,0.3224529,0.0001767907,0.6128151],"study_design_scores_gemma":[0.0002144057,0.00007513165,0.000204098,0.00002014114,0.000001509798,0.00001251936,0.00003893586,0.9805729,0.01739914,0.001295445,0.00002091286,0.0001448948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2772067,0.0001212631,0.7077587,0.00006624765,0.0002383902,0.00005304586,1.380917e-7,0.0001712478,0.01438436],"genre_scores_gemma":[0.8837935,9.084196e-7,0.1131772,0.0002310331,0.0001717486,0.000005080019,2.352207e-7,0.000005439789,0.002614915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778537,"threshold_uncertainty_score":0.3366861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02114323554206217,"score_gpt":0.2839945996636008,"score_spread":0.2628513641215386,"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."}}