{"id":"W169063832","doi":"10.63317/2ghqfd9j9xh9","title":"A French Human Reference Corpus for Multi-Document Summarization and Sentence Compression","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Natural language processing; Multi-document summarization; Artificial intelligence; Sentence; Information retrieval; Compression (physics)","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":[0.003633909,0.001697305,0.00136965,0.006154488,0.002452759,0.001797162,0.00138691,0.001959309,0.02763339],"category_scores_gemma":[0.01010138,0.0003905945,0.0007010418,0.003658764,0.0007726534,0.001504325,0.001231894,0.001073267,0.01250263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378374,"about_ca_system_score_gemma":0.003112436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02775894,"about_ca_topic_score_gemma":0.02522557,"domain_scores_codex":[0.9958143,0.002163925,0.0003007239,0.0007786237,0.0007335327,0.0002090261],"domain_scores_gemma":[0.9893124,0.003569505,0.0002586803,0.001425046,0.005083644,0.0003508493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001095868,0.0005608418,0.002134649,0.003532469,0.0001994112,0.001699044,0.001490991,0.006417004,0.04757725,0.006214428,0.4041951,0.524883],"study_design_scores_gemma":[0.0005890031,0.0009314514,0.02347475,0.0007069369,0.0005004879,0.003872097,0.001715133,0.0354522,0.08441817,0.004177558,0.843882,0.0002801708],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1959525,0.02247491,0.3266158,0.005669836,0.00398514,0.00336504,0.325719,0.04095802,0.07525995],"genre_scores_gemma":[0.2262232,0.0034181,0.2244327,0.0008102228,0.0009934473,0.002386163,0.4994074,0.003081001,0.03924778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02775894,"threshold_uncertainty_score":0.09244293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04659203308536194,"score_gpt":0.3394436589713973,"score_spread":0.2928516258860354,"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."}}