{"id":"W4385570349","doi":"10.18653/v1/2023.findings-acl.215","title":"Varta: A Large-Scale Headline-Generation Dataset for Indic Languages","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Headline; Computer science; Natural language processing; Artificial intelligence; Scale (ratio); Variety (cybernetics); Information retrieval; Data science; Linguistics; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001002587,0.001699349,0.0007060664,0.005027285,0.001364083,0.00141195,0.001546103,0.001619874,0.01434573],"category_scores_gemma":[0.00591154,0.0004241623,0.0009559856,0.004474122,0.000527666,0.001947942,0.001510342,0.001659681,0.01842492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008624648,"about_ca_system_score_gemma":0.001728098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01222862,"about_ca_topic_score_gemma":0.03175827,"domain_scores_codex":[0.9988964,0.0002671681,0.0001503803,0.000287462,0.0002840623,0.0001144275],"domain_scores_gemma":[0.9966395,0.001120751,0.0003174171,0.0006618664,0.0009333391,0.0003271231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003283647,0.0002987634,0.006040018,0.001623134,0.00009930126,0.0006334532,0.0006565669,0.00173902,0.004810756,0.00128085,0.9374108,0.04507912],"study_design_scores_gemma":[0.0005691065,0.0002255601,0.0244977,0.0003126925,0.0001541191,0.001298855,0.00161573,0.01951983,0.01212343,0.002236714,0.9372684,0.0001777951],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03430933,0.001480301,0.006109328,0.0006296998,0.0004765839,0.000428523,0.929171,0.01530147,0.01209382],"genre_scores_gemma":[0.01400904,0.000210274,0.009002594,0.0001453353,0.00007492881,0.000292681,0.9735149,0.0004866123,0.002263741],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01434573,"threshold_uncertainty_score":0.04799128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05068896009991682,"score_gpt":0.3264950599578167,"score_spread":0.2758060998578999,"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."}}