{"id":"W2945479974","doi":"10.1007/978-3-030-18305-9_2","title":"Weakly Supervised, Data-Driven Acquisition of Rules for Open Information Extraction","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Relationship extraction; Lemma (botany); Rank (graph theory); Natural language processing; Information extraction; Sentence; Relation (database); Recall; Artificial intelligence; Precision and recall; Quality (philosophy); Sequence (biology); Data mining; Information retrieval","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":[0.003502177,0.0007938516,0.001254139,0.002381287,0.0008866814,0.003144064,0.003051057,0.001391475,0.003051356],"category_scores_gemma":[0.01789365,0.0007259584,0.001298128,0.001833802,0.001078378,0.003900628,0.003218316,0.00285526,0.003916704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008235035,"about_ca_system_score_gemma":0.002324259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001593421,"about_ca_topic_score_gemma":0.005569309,"domain_scores_codex":[0.9959542,0.001087719,0.0004843315,0.0009776085,0.001230332,0.0002658429],"domain_scores_gemma":[0.9799645,0.01174842,0.0008574306,0.003314487,0.003718812,0.0003963466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004608655,0.0005994996,0.005956656,0.0005133061,0.0001431706,0.000379139,0.0004942837,0.0199785,0.04688025,0.01166734,0.01270907,0.9002178],"study_design_scores_gemma":[0.00004941704,0.0002055612,0.002643681,0.0001311426,0.00008575041,0.0004399032,0.0003352062,0.8559617,0.08002192,0.04836732,0.01169579,0.00006249462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03610815,0.0003786998,0.9522317,0.0003222949,0.00006435131,0.000301619,0.001585278,0.005726265,0.003281599],"genre_scores_gemma":[0.1984866,0.0002104475,0.7882479,0.0002214603,0.00008303274,0.0003680199,0.008600136,0.0005388799,0.003243635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003502177,"threshold_uncertainty_score":0.01852149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02814080462584018,"score_gpt":0.3042700418758993,"score_spread":0.2761292372500592,"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."}}