{"id":"W2805480372","doi":"10.63317/3tat2guzqfur","title":"A New Annotated Portuguese/Spanish Corpus for the Multi-Sentence Compression Task","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Portuguese; Natural language processing; Sentence; Task (project management); Artificial intelligence; Compression (physics); Speech recognition; Linguistics; Engineering","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":[0.0005065177,0.0003925685,0.0004392562,0.00009512887,0.0002335628,0.0004536033,0.003318042,0.0003083638,0.00003731854],"category_scores_gemma":[0.0001867509,0.0002429648,0.0002560689,0.0002283421,0.00008981382,0.0001874282,0.002412265,0.0003478357,0.0001786353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005504511,"about_ca_system_score_gemma":0.0005173943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00337959,"about_ca_topic_score_gemma":0.0002927986,"domain_scores_codex":[0.9973252,0.00009723784,0.00053152,0.001034616,0.000482748,0.0005286437],"domain_scores_gemma":[0.9965352,0.0003446023,0.0004271418,0.001984226,0.0004194356,0.0002893574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001475121,0.0002492005,0.001047813,0.0002503527,0.0002494621,0.00005121178,0.001517122,0.0005155581,0.004336386,0.005464014,0.8360307,0.1501407],"study_design_scores_gemma":[0.002897211,0.0003703783,0.009955065,0.0007576263,0.00007615829,0.00009458747,0.0001212728,0.8477511,0.007881277,0.0112178,0.117437,0.001440597],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003359446,0.001209457,0.9862248,0.001072004,0.007752475,0.001821577,0.00005129898,0.000547428,0.0009850404],"genre_scores_gemma":[0.1353751,0.0003469109,0.8361278,0.002253541,0.003037343,0.0005556481,0.0002864814,0.0001020163,0.02191518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8472355,"threshold_uncertainty_score":0.9907818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05372594388695155,"score_gpt":0.2942539148323845,"score_spread":0.2405279709454329,"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."}}