{"id":"W2594363579","doi":"10.1016/j.ipm.2017.02.009","title":"Self-training on refined clause patterns for relation extraction","year":2017,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relationship extraction; Computer science; Parsing; Information extraction; Natural language processing; Dependency (UML); Context (archaeology); Relation (database); Dependency grammar; Benchmark (surveying); Variety (cybernetics); Artificial intelligence; Rule-based machine translation; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004404062,0.0001037882,0.00008098396,0.0001572462,0.0007284568,0.001195623,0.0005186204,0.00006564937,0.000002846988],"category_scores_gemma":[0.00004453123,0.0001038663,0.00003274182,0.00005011767,0.000006773416,0.00565047,0.0001157881,0.000105458,0.00004220119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009951924,"about_ca_system_score_gemma":0.00002393499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004042574,"about_ca_topic_score_gemma":0.000001904771,"domain_scores_codex":[0.9990392,0.000009026984,0.0003230209,0.0001714451,0.0002738102,0.0001835346],"domain_scores_gemma":[0.9988373,0.0000183635,0.0004730758,0.0005386146,0.00009765133,0.00003502403],"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":[0.000008728995,0.00001654822,0.00007182766,0.000262317,0.00001202763,7.431606e-7,0.002285732,0.001256968,0.000003678544,0.05159429,0.0001927895,0.9442943],"study_design_scores_gemma":[0.000859659,0.00004154648,0.01867223,0.0002231833,0.00001795231,0.000002901382,0.0002646491,0.8981126,0.0001093185,0.005264182,0.07620309,0.0002286749],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003961409,0.000003564817,0.9716977,0.002022933,0.0003999504,0.0003665854,9.772191e-7,0.000305533,0.02124138],"genre_scores_gemma":[0.8144553,0.000008084481,0.1844223,0.0006515058,0.00006324818,0.00009856357,0.00001321077,0.000005691776,0.0002821158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9440657,"threshold_uncertainty_score":0.9998412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04563325351583229,"score_gpt":0.3055209064605257,"score_spread":0.2598876529446934,"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."}}