{"id":"W2530085701","doi":"10.1007/978-3-319-48051-0_12","title":"Constraining Word Embeddings by Prior Knowledge – Application to Medical Information Retrieval","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Word (group theory); Natural language processing; Word embedding; Artificial intelligence; Embedding; Domain (mathematical analysis); Information retrieval; Linguistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002777004,0.001318208,0.001500405,0.002628072,0.0007032456,0.002200974,0.001662614,0.002030655,0.0033885],"category_scores_gemma":[0.01371787,0.001079906,0.001407539,0.003762251,0.0009166686,0.00543113,0.0027512,0.002596213,0.002093414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00061958,"about_ca_system_score_gemma":0.001036943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005444762,"about_ca_topic_score_gemma":0.006248355,"domain_scores_codex":[0.998611,0.0005163926,0.0001526701,0.0004043176,0.0002192135,0.00009653618],"domain_scores_gemma":[0.9930173,0.004976389,0.0003302301,0.0007460467,0.0007894242,0.0001405192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004416301,0.0003443327,0.00159736,0.0004219366,0.0001650582,0.0001653425,0.0002928681,0.1188923,0.007075059,0.01097063,0.01212805,0.8475055],"study_design_scores_gemma":[0.00004540977,0.00007528749,0.000740643,0.00005499962,0.00005936468,0.0001329918,0.00008687771,0.9534811,0.002109905,0.0403014,0.002878423,0.00003352697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03547771,0.002398948,0.9567129,0.0006443726,0.0001744951,0.00009204434,0.0005587158,0.001985264,0.001955526],"genre_scores_gemma":[0.4054471,0.002834352,0.5780576,0.0004039743,0.0006054967,0.0002736521,0.004482773,0.0008995199,0.006995451],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005444762,"threshold_uncertainty_score":0.01468641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01194298202140937,"score_gpt":0.2622342695910949,"score_spread":0.2502912875696855,"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."}}