{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001904935,0.002220789,0.001341936,0.004035085,0.001722676,0.00153739,0.001411717,0.001420865,0.03168593],"category_scores_gemma":[0.005591171,0.0005049259,0.0005735234,0.003351385,0.000706411,0.001180852,0.002079469,0.001512854,0.01358134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007094297,"about_ca_system_score_gemma":0.002840961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01243822,"about_ca_topic_score_gemma":0.01591602,"domain_scores_codex":[0.998428,0.0004176004,0.0001729659,0.0004502935,0.0003931464,0.0001381256],"domain_scores_gemma":[0.9954823,0.0009787639,0.0001568612,0.0006953049,0.002397191,0.000289528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001811073,0.001081517,0.004595343,0.005577395,0.0001908798,0.004206639,0.003074746,0.003460007,0.1245818,0.005232033,0.464131,0.3820576],"study_design_scores_gemma":[0.0008391644,0.0003483091,0.04814468,0.0006381664,0.0003465755,0.003915583,0.002589932,0.0105435,0.03951683,0.003231624,0.889663,0.0002228077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.246253,0.007011882,0.09234142,0.00268442,0.004476388,0.002465005,0.5252734,0.01413057,0.1053639],"genre_scores_gemma":[0.1464801,0.001714202,0.09534812,0.0006011113,0.0009585959,0.00274474,0.7165045,0.005278282,0.03037023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03168593,"threshold_uncertainty_score":0.1059999,"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."}}