{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006692391,0.002038999,0.001256786,0.003417083,0.002583439,0.004703754,0.003620769,0.001916514,0.007652295],"category_scores_gemma":[0.01705064,0.001622366,0.001590408,0.003903338,0.001325037,0.01421861,0.005407671,0.003695731,0.01235913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510918,"about_ca_system_score_gemma":0.00382365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01818051,"about_ca_topic_score_gemma":0.03735367,"domain_scores_codex":[0.9969115,0.001318325,0.0002277172,0.0009641749,0.000359957,0.0002184151],"domain_scores_gemma":[0.9913968,0.003284262,0.0002699827,0.002380645,0.002093469,0.0005748737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001617195,0.001598733,0.01679928,0.00251373,0.0005465225,0.001093637,0.003604798,0.03496327,0.01675234,0.02752589,0.3664266,0.5265579],"study_design_scores_gemma":[0.0007125947,0.0009542112,0.01403538,0.0009622621,0.0007577823,0.001498908,0.009223645,0.4753,0.03274402,0.05616657,0.4072361,0.0004084858],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2686054,0.01153244,0.4558214,0.008316102,0.00278783,0.001427335,0.1047383,0.09047675,0.0562944],"genre_scores_gemma":[0.3369284,0.002307434,0.3056955,0.001223748,0.0003571472,0.001362377,0.3285362,0.009684571,0.01390456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01818051,"threshold_uncertainty_score":0.03614938,"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."}}