{"id":"W2096223775","doi":"10.3115/1613715.1613823","title":"Complexity of finding the BLEU-optimal hypothesis in a confusion network","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Defense Advanced Research Projects Agency","keywords":"BLEU; Confusion; Computer science; Metric (unit); Translation (biology); Artificial intelligence; Representation (politics); Word (group theory); Machine translation; Simple (philosophy); Time complexity; Natural language processing; Theoretical computer science; Algorithm; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005601167,0.001137634,0.002681849,0.001924013,0.001976873,0.005500004,0.002732547,0.003464887,0.009444548],"category_scores_gemma":[0.04991028,0.001048437,0.001514278,0.002669603,0.002189746,0.009507718,0.003443568,0.002915812,0.001679127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003903383,"about_ca_system_score_gemma":0.003159333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0054122,"about_ca_topic_score_gemma":0.004548942,"domain_scores_codex":[0.9924959,0.003530084,0.0004442139,0.001857125,0.001104964,0.0005677099],"domain_scores_gemma":[0.9488642,0.04612985,0.001122365,0.001970207,0.001329091,0.0005843159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002219665,0.0004701857,0.01044766,0.001417079,0.0004079549,0.0006745491,0.001098259,0.5796991,0.006142127,0.07739761,0.03131216,0.2887136],"study_design_scores_gemma":[0.0001629418,0.0001273825,0.001991279,0.00005557489,0.00007478554,0.0002438153,0.0003082565,0.7628509,0.002447647,0.2302357,0.00144197,0.00005973653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3322169,0.001928729,0.6285031,0.009586108,0.0002050945,0.0006315839,0.007000694,0.003475216,0.01645266],"genre_scores_gemma":[0.7967283,0.0008585091,0.1862164,0.0008505203,0.0002699832,0.0006111634,0.009462709,0.0007446407,0.004257788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009444548,"threshold_uncertainty_score":0.03159511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06938032207941744,"score_gpt":0.272355908408229,"score_spread":0.2029755863288116,"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."}}