{"id":"W2132959801","doi":"","title":"Incremental Segmentation and Decoding Strategies for Simultaneous Translation","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Decoding methods; Segmentation; Artificial intelligence; Machine translation; Speech recognition; Interpreter; Natural language processing; Speech translation; Active listening; Phrase; Task (project management); Latency (audio); Translation (biology); Algorithm; Programming language; Communication","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001496184,0.0002000225,0.0001483285,0.0002014802,0.0001644538,0.001361609,0.0004334668,0.00007401322,0.00003330427],"category_scores_gemma":[0.0001104333,0.0001697447,0.00004422136,0.0001206145,0.00004751436,0.002215149,0.00008169207,0.0002063894,0.000007195307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009233644,"about_ca_system_score_gemma":0.0000783294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006760581,"about_ca_topic_score_gemma":0.00001562517,"domain_scores_codex":[0.9987131,0.00002789982,0.0002836843,0.0004081634,0.0003430737,0.0002240612],"domain_scores_gemma":[0.9991647,0.000130876,0.0001836178,0.0001219667,0.0003417619,0.00005707993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001477135,0.0000205822,0.000009821551,0.00004822163,0.0000120124,0.000008011119,0.001676693,0.00001235389,0.1667779,0.01660419,0.00002368877,0.8147917],"study_design_scores_gemma":[0.0005876113,0.0001004308,0.00005304594,0.0002772257,0.000008751598,0.00005233152,0.001781555,0.9094615,0.05677022,0.03051396,0.00002579699,0.0003675582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0474139,0.004268515,0.9428076,0.002857871,0.0003440022,0.0007298377,0.00001028748,0.0005874271,0.0009805585],"genre_scores_gemma":[0.663362,0.000009569244,0.3360689,0.0003517382,0.00006163484,0.00006151719,0.00002500261,0.000009098106,0.00005055283],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9094492,"threshold_uncertainty_score":0.9996751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02833968079378524,"score_gpt":0.3111720211243554,"score_spread":0.2828323403305702,"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."}}