{"id":"W3173628900","doi":"10.1609/aaai.v35i15.17632","title":"Progressive Multi-task Learning with Controlled Information Flow for Joint Entity and Relation Extraction","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Beijing Advanced Innovation Center for Big Data and Brain Computing; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Multi-task learning; Computer science; Benchmark (surveying); Artificial intelligence; Task (project management); Machine learning; Joint (building); Relation (database); Representation (politics); Relationship extraction; Exploit; Feature learning; Information extraction; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004495538,0.0001379136,0.0002123828,0.00009487271,0.0003231468,0.0004702414,0.0002387683,0.0000673344,0.00001562986],"category_scores_gemma":[0.001153031,0.0001016386,0.00006772443,0.0003177715,0.00009964734,0.001289583,0.00009003431,0.0002567926,0.00001209048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003403339,"about_ca_system_score_gemma":0.0001043091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005304524,"about_ca_topic_score_gemma":0.000003727054,"domain_scores_codex":[0.9987914,0.00002959286,0.0004211158,0.0002633549,0.0003129878,0.0001815298],"domain_scores_gemma":[0.9979359,0.0001137748,0.000580815,0.0001072538,0.001206464,0.00005578311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005555683,0.0001630739,0.0004634749,0.0001137262,0.00005076901,0.000001119223,0.006708832,0.003218075,0.03312699,0.6741316,0.00001818013,0.2814486],"study_design_scores_gemma":[0.0003631044,0.0002069836,0.000885315,0.0001550362,0.00001947466,0.00001671192,0.001605779,0.9243695,0.06357725,0.008405274,0.0002466426,0.0001489997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.052775,0.00004523312,0.9426493,0.001871844,0.000215736,0.0008355762,0.000001828701,0.00009219436,0.001513276],"genre_scores_gemma":[0.9435814,0.00002250437,0.05604297,0.00007095582,0.00002289048,0.00007468246,0.000002859381,0.000005720711,0.0001760352],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9211513,"threshold_uncertainty_score":0.4534548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06065020142216308,"score_gpt":0.2900157999577008,"score_spread":0.2293655985355377,"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."}}