{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00182161,0.001329773,0.0009257125,0.002613437,0.0006984726,0.001138187,0.002101846,0.001475108,0.01571956],"category_scores_gemma":[0.007977788,0.0007649405,0.001298217,0.002439287,0.0004351487,0.003998228,0.002087541,0.002437027,0.007849737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004568661,"about_ca_system_score_gemma":0.001450986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004323009,"about_ca_topic_score_gemma":0.009098784,"domain_scores_codex":[0.9985186,0.0003280845,0.0001642513,0.0005627368,0.0002556088,0.0001707391],"domain_scores_gemma":[0.9946896,0.003081423,0.0001889775,0.001046715,0.0008404534,0.000152761],"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":[0.0004298951,0.000352403,0.005010174,0.0003337984,0.0001333878,0.000235702,0.000412582,0.007697076,0.02069696,0.003558997,0.02833118,0.9328078],"study_design_scores_gemma":[0.0001731538,0.0003292686,0.005236605,0.0001971669,0.0003101108,0.0007660008,0.0007039172,0.8986702,0.03998945,0.02156246,0.03200921,0.00005243866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09005117,0.001207824,0.8657445,0.0007960121,0.0004213075,0.0005742434,0.003935187,0.02938965,0.00788014],"genre_scores_gemma":[0.3590282,0.0004998277,0.6088818,0.0005496652,0.0002016255,0.0004225118,0.01842267,0.001604245,0.01038948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01571956,"threshold_uncertainty_score":0.05258715,"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."}}