{"id":"W3108142956","doi":"10.3233/faia200860","title":"Sentence Embeddings and High-Speed Similarity Search for Fast Computer Assisted Annotation of Legal Documents","year":2020,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Annotation; Computer science; Sentence; Natural language processing; Artificial intelligence; Similarity (geometry); Meaning (existential); Process (computing); Information retrieval; Interface (matter); Programming language; Image (mathematics)","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":[0.0001916467,0.0001918722,0.0003277011,0.0001791435,0.0001242641,0.0001444152,0.0004074055,0.000150445,0.000002870044],"category_scores_gemma":[0.000008520755,0.0002136044,0.00005351725,0.0001216344,0.0001747945,0.0002445219,0.0002059719,0.0002354634,0.000003025382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004377816,"about_ca_system_score_gemma":0.00005882051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005499411,"about_ca_topic_score_gemma":0.000015124,"domain_scores_codex":[0.9984345,0.00001601324,0.0005236852,0.0006326424,0.000214038,0.0001791461],"domain_scores_gemma":[0.9991888,0.00007449445,0.0001801348,0.0003040949,0.0001614736,0.00009100745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001327364,0.00002469204,0.00005742208,0.0000763114,0.00002111479,0.000001235996,0.0004297985,0.0006813247,0.0001096435,0.600785,0.0001676121,0.3976326],"study_design_scores_gemma":[0.00006812211,0.0000847085,0.0000613878,0.0001115734,0.00002668166,0.000003398895,0.0001457953,0.736789,0.001622184,0.2540345,0.006744208,0.0003083984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001944101,0.0001467698,0.9964604,0.000897726,0.0001956684,0.0008251955,0.00005028445,0.00003644164,0.001193038],"genre_scores_gemma":[0.2197941,0.0005266687,0.7741147,0.0004566465,0.0005511487,0.0001882318,0.0001516153,0.00005398879,0.004162858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7361076,"threshold_uncertainty_score":0.8710533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05354764576486624,"score_gpt":0.2979148153250844,"score_spread":0.2443671695602181,"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."}}