{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002506326,0.001289127,0.001118552,0.000620133,0.0005147309,0.000894787,0.002672696,0.001420485,0.001965106],"category_scores_gemma":[0.005921136,0.000612263,0.001203958,0.001065802,0.001030823,0.003420641,0.0025998,0.003142655,0.0006945996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001084438,"about_ca_system_score_gemma":0.001419558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003948431,"about_ca_topic_score_gemma":0.004711137,"domain_scores_codex":[0.9991893,0.0002585762,0.00004626079,0.0002675208,0.0001398313,0.0000985018],"domain_scores_gemma":[0.9979929,0.001015438,0.000188869,0.0004635318,0.0002212054,0.0001181117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004887863,0.0006651267,0.001944268,0.0002303576,0.0001621235,0.0002646653,0.0003203789,0.6510473,0.0123591,0.01901272,0.004114731,0.3093903],"study_design_scores_gemma":[0.00001310655,0.00004203285,0.00009579051,0.000003428134,0.0000092362,0.00001374174,0.000005975875,0.9882541,0.001156661,0.01011883,0.0002815891,0.0000055705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03062645,0.0003998021,0.9661419,0.0002939814,0.00004216226,0.0001032807,0.0001052396,0.001185575,0.001101592],"genre_scores_gemma":[0.7704688,0.0003121734,0.2237498,0.0003808668,0.00008846661,0.0003940135,0.0005649702,0.0001423918,0.00389857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003948431,"threshold_uncertainty_score":0.01325488,"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."}}