{"id":"W2143177362","doi":"10.3115/v1/w14-3346","title":"A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; National Research Council Canada","funders":"","keywords":"BLEU; Computer science; Smoothing; Sentence; Artificial intelligence; Natural language processing; Speech recognition; Machine translation; Computer vision","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":[0.0007905922,0.0001231353,0.0003907393,0.0001322938,0.0000677969,0.00009715249,0.001013984,0.00007578534,0.000001536806],"category_scores_gemma":[0.0004217426,0.00008993206,0.00007932838,0.0002172997,0.0000324988,0.0003294496,0.0001813033,0.0000894777,0.000001886369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002573919,"about_ca_system_score_gemma":0.0000240733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003986456,"about_ca_topic_score_gemma":0.000007286357,"domain_scores_codex":[0.9988181,0.00006059819,0.0004489431,0.0002469308,0.0002367548,0.0001886784],"domain_scores_gemma":[0.998652,0.0003231307,0.0002790514,0.0004895235,0.0002175771,0.00003875708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008207312,0.0001429591,0.0002935067,0.02156883,0.00003928995,8.986405e-7,0.0018676,0.000002512659,0.03426877,0.8914568,0.002244297,0.04810635],"study_design_scores_gemma":[0.0001253629,0.0002017043,0.000007787126,0.003784331,0.00002001945,0.00001055707,0.00009210113,0.1812883,0.740885,0.07321411,0.0001196049,0.0002511225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002412115,0.0003833884,0.996826,0.0002561978,0.00006215281,0.0005247073,0.000001001273,0.0009433026,0.00076204],"genre_scores_gemma":[0.4299718,6.008494e-7,0.5697259,0.0001163916,0.0000135965,0.0000536385,5.374234e-7,0.000005391757,0.0001121484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8182427,"threshold_uncertainty_score":0.3667323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03508668186407472,"score_gpt":0.3199661980098258,"score_spread":0.2848795161457511,"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."}}