{"id":"W2739730962","doi":"10.18653/v1/s17-1026","title":"Generating Pattern-Based Entailment Graphs for Relation Extraction","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Logical consequence; Relation (database); Computer science; Textual entailment; Relationship extraction; Structuring; Artificial intelligence; Natural language processing; Task (project management); Meaning (existential); Exploit; Semantic relation; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001814483,0.00005079288,0.00004460664,0.00003059551,0.0003805918,0.000270529,0.0002955853,0.00002821074,0.000009841539],"category_scores_gemma":[0.00002634183,0.00004681283,0.00003786072,0.00001221902,0.000005726867,0.0004474325,0.00003879843,0.00003590836,0.000005839431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000253645,"about_ca_system_score_gemma":0.00001726446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007266158,"about_ca_topic_score_gemma":0.00002789822,"domain_scores_codex":[0.9994625,0.00001073202,0.0001178214,0.0001998651,0.0001048463,0.0001042263],"domain_scores_gemma":[0.9993155,0.00003156953,0.0001049035,0.0004886359,0.00003308485,0.00002630374],"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":[0.000003822395,0.00004998764,0.01984063,0.00002236821,0.00001058508,0.000002228313,0.00019692,0.02361237,0.01462561,0.06514403,0.0004119285,0.8760795],"study_design_scores_gemma":[0.0002926002,0.00001787735,0.004432852,0.000006847988,0.000001837821,5.843634e-7,0.0000035613,0.9864848,0.006527845,0.001828411,0.000340255,0.00006254802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06910073,0.000004977527,0.9284068,0.001216184,0.0004444105,0.000140075,2.960147e-7,0.00006712443,0.000619353],"genre_scores_gemma":[0.7762784,4.296428e-7,0.223238,0.0002338749,0.00005600214,0.00002323061,0.000001533431,0.000002677713,0.000165804],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9628724,"threshold_uncertainty_score":0.2927243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05132058273999077,"score_gpt":0.3067872736571209,"score_spread":0.2554666909171301,"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."}}