{"id":"W4293083978","doi":"10.1145/3533020","title":"Learning Implicit and Explicit Multi-task Interactions for Information Extraction","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Key Research and Development Program of China","keywords":"Computer science; Multi-task learning; Generalization; Leverage (statistics); Artificial intelligence; Task (project management); Machine learning; Sequence learning; Unobservable; Representation (politics)","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":[0.002046105,0.001782225,0.0009503917,0.0005885588,0.0006145194,0.0009032622,0.002028205,0.001306113,0.001633325],"category_scores_gemma":[0.007025431,0.000654783,0.001265249,0.0007241819,0.0007797832,0.003839209,0.002373164,0.003274332,0.0008135953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000921466,"about_ca_system_score_gemma":0.00103243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003114056,"about_ca_topic_score_gemma":0.006202245,"domain_scores_codex":[0.9988242,0.0003354883,0.00006866879,0.0004259956,0.000208399,0.0001373061],"domain_scores_gemma":[0.9974469,0.001416294,0.0002454192,0.0004675387,0.0002993586,0.0001244251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000484102,0.0006103599,0.005945704,0.0003428423,0.0003443598,0.0005862784,0.0006781832,0.4529666,0.03813067,0.02802095,0.006107283,0.4657827],"study_design_scores_gemma":[0.000007064311,0.00005540964,0.0004841266,0.000007127169,0.00002717159,0.0000413275,0.00001289787,0.9842481,0.004296119,0.009989522,0.0008183431,0.00001275773],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0320079,0.0006685317,0.9634356,0.0003934295,0.00006142252,0.00008167795,0.0001476208,0.00122543,0.001978412],"genre_scores_gemma":[0.7252665,0.000668671,0.2671406,0.0004367343,0.0001250996,0.0002950853,0.001048291,0.0002221979,0.004796876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003114056,"threshold_uncertainty_score":0.01082098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02740170172849626,"score_gpt":0.2773413987875704,"score_spread":0.2499396970590741,"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."}}