{"id":"W4385570009","doi":"10.18653/v1/2023.acl-long.693","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Ministry of Electronics and Information technology","keywords":"Computer science; Benchmark (surveying); Linguistics; Natural language processing; Artificial intelligence; Volume (thermodynamics); Computational linguistics; Programming language; Geography; Philosophy","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":[0.0006831017,0.0002563183,0.0002796731,0.0004763204,0.0002369007,0.0003814187,0.000956936,0.0001710464,0.00001384319],"category_scores_gemma":[0.0002364412,0.0002239405,0.00007623119,0.000489638,0.00005933076,0.0008962671,0.0007233776,0.0002654259,0.00001160385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005428055,"about_ca_system_score_gemma":0.00009847457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002833522,"about_ca_topic_score_gemma":0.00003586297,"domain_scores_codex":[0.9981739,0.00003882172,0.0002865487,0.000616852,0.0003414732,0.0005424324],"domain_scores_gemma":[0.9989794,0.0001895333,0.0001573367,0.0004381952,0.0001051117,0.0001304613],"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":[0.00003266643,0.00006323084,0.0005221232,0.0004333357,0.00008230185,0.000341915,0.02201784,0.0001052082,0.03339847,0.137993,0.004845162,0.8001647],"study_design_scores_gemma":[0.001574272,0.000529447,0.000905406,0.0005080849,0.00006535959,0.0001956201,0.00223043,0.5074667,0.2015204,0.2821729,0.0007809655,0.002050327],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2704763,0.003542063,0.7186261,0.0005305562,0.0003114238,0.0006700108,0.0000434629,0.003918334,0.001881807],"genre_scores_gemma":[0.5927073,0.00002768644,0.4062929,0.000273211,0.0001193845,0.00004259204,0.00001811009,0.00002392523,0.0004948887],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7981144,"threshold_uncertainty_score":0.9132029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01818371428975249,"score_gpt":0.3075003750777553,"score_spread":0.2893166607880028,"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."}}