{"id":"W3209039755","doi":"10.18653/v1/2021.emnlp-main.821","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universitas Indonesia; York University; Samsung; National Science Foundation","keywords":"Annotation; Indonesian; Sentence; Test set; Set (abstract data type); Inference; Data set","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001189104,0.00035333,0.0005679241,0.0002156662,0.0001766001,0.0004095632,0.00204899,0.0001911326,0.00001641295],"category_scores_gemma":[0.004242244,0.0002563889,0.0001544448,0.001421815,0.0001262284,0.0008144082,0.001001663,0.001035344,0.000001789162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001072036,"about_ca_system_score_gemma":0.0003976043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002483911,"about_ca_topic_score_gemma":0.00002147299,"domain_scores_codex":[0.9971326,0.0001426829,0.0006491729,0.0009387123,0.0005470959,0.0005897254],"domain_scores_gemma":[0.9978175,0.0005991604,0.0004222767,0.0004970225,0.0005575809,0.0001064947],"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":[0.00006070506,0.0001450058,0.001691619,0.0004837433,0.00002523101,0.00001879834,0.007102371,0.00001353722,0.1052891,0.00727343,0.0001371231,0.8777593],"study_design_scores_gemma":[0.001893794,0.0001187055,0.002991418,0.001898179,0.00006099793,0.00009603138,0.006483946,0.657691,0.3147393,0.01225447,0.0006293923,0.001142726],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4812248,0.0240161,0.4641148,0.02112343,0.002969742,0.002420486,0.0002827436,0.000374964,0.003472929],"genre_scores_gemma":[0.5931575,0.00000937684,0.4058751,0.0006722309,0.00008595378,0.00003906156,0.00001948997,0.00001456661,0.000126734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8766165,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06648941278896932,"score_gpt":0.43358885394361,"score_spread":0.3670994411546407,"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."}}