{"id":"W3205430877","doi":"10.1007/978-3-030-88483-3_23","title":"Towards Unifying the Explainability Evaluation Methods for NLP","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Phrase; Metric (unit); Set (abstract data type); Machine learning; Feature (linguistics); Focus (optics); Natural language; Deep learning; Key (lock); Natural language processing; Training set","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":[0.008999621,0.0004060378,0.0004534255,0.0003080188,0.0004769225,0.0007056829,0.003609859,0.0002688881,0.00002092213],"category_scores_gemma":[0.001109541,0.0003085532,0.0002027952,0.0005265957,0.0003932636,0.0004886683,0.00159508,0.0006573989,0.000002814061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006347698,"about_ca_system_score_gemma":0.001733642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002179846,"about_ca_topic_score_gemma":0.00005250038,"domain_scores_codex":[0.9957807,0.0002530063,0.0005642761,0.001739432,0.001082723,0.000579853],"domain_scores_gemma":[0.9948618,0.00158281,0.0002650271,0.002274316,0.0009139667,0.0001020404],"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":[0.000001479525,0.000007779719,0.000003591775,0.00003206339,0.00000660259,0.000002755859,0.0008312101,0.04074488,0.00007630965,0.04364672,0.000003538575,0.914643],"study_design_scores_gemma":[0.0001223776,0.00003519439,0.00002085787,0.00009706109,0.00001136624,0.00001656293,5.324767e-7,0.6675225,0.00126005,0.3284508,0.002215857,0.0002468411],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003177029,0.00125434,0.990174,0.00303581,0.002778082,0.001070222,0.000002304664,0.00009672056,0.001556757],"genre_scores_gemma":[0.01555667,0.00001735058,0.982515,0.001195497,0.0004770043,0.00007620413,0.000004352697,0.0000215225,0.0001363901],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9143962,"threshold_uncertainty_score":0.9999366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08998709768257471,"score_gpt":0.3780216545665107,"score_spread":0.288034556883936,"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."}}