{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003064024,0.00007458885,0.0001278525,0.00005244437,0.0001147501,0.00002262631,0.0007786845,0.00004127668,0.00002388009],"category_scores_gemma":[0.00005721207,0.00004622652,0.00003468715,0.0004500204,0.0001527014,0.0001799505,0.0002843075,0.0001292964,0.000003747521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002074549,"about_ca_system_score_gemma":0.00003659162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001353442,"about_ca_topic_score_gemma":0.00002953667,"domain_scores_codex":[0.9992526,0.0000586089,0.0001747809,0.0001610659,0.0001703139,0.0001826535],"domain_scores_gemma":[0.9993783,0.0001810383,0.00007768301,0.0003060578,0.00003695393,0.00001991536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004401151,0.0001795373,0.01051618,0.00005039241,0.00002047117,0.0001176849,0.004769301,0.0006928601,0.009693695,0.8937204,0.008981831,0.07121365],"study_design_scores_gemma":[0.0009740863,0.0002779944,0.04185342,0.0003617737,0.00001121807,0.0003484291,0.0001241375,0.3157825,0.1848142,0.4533279,0.001258564,0.0008657906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2479836,0.00115634,0.7428382,0.001899621,0.00009030176,0.0002753121,8.160919e-7,0.0004657843,0.005290037],"genre_scores_gemma":[0.5658371,0.000009459443,0.4338643,0.0001975742,0.00001361141,0.000002662461,1.335659e-7,0.00000215998,0.00007289878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4403925,"threshold_uncertainty_score":0.1885063,"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."}}