{"id":"W3217040326","doi":"10.1145/3471165","title":"Dual Gated Graph Attention Networks with Dynamic Iterative Training for Cross-Lingual Entity Alignment","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Research Foundation Singapore","keywords":"Computer science; Attention network; Graph; Embedding; Iterative and incremental development; Benchmark (surveying); Dual (grammatical number); Process (computing); Machine learning; Artificial intelligence; Theoretical computer science; 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":[0.0009887434,0.001402024,0.001077224,0.001078782,0.0007655739,0.0008003276,0.002870952,0.001681183,0.002961066],"category_scores_gemma":[0.004456244,0.0006809248,0.0007597976,0.001639331,0.0007975723,0.002581698,0.002063663,0.002267432,0.0009640171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581468,"about_ca_system_score_gemma":0.001672767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02475445,"about_ca_topic_score_gemma":0.04707427,"domain_scores_codex":[0.9993292,0.0001922084,0.00002896983,0.0002724828,0.00008262714,0.00009455467],"domain_scores_gemma":[0.9988396,0.0005812141,0.00008448759,0.0002105988,0.0002131069,0.00007092748],"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":[0.0002309442,0.0002501699,0.003295612,0.0001378164,0.0001432826,0.000246728,0.0002928325,0.5945234,0.005244368,0.009983409,0.008744049,0.3769074],"study_design_scores_gemma":[0.000008814662,0.00002492102,0.000243216,0.000007175132,0.00001996897,0.00002494118,0.00002237607,0.9925694,0.0006853624,0.005519472,0.0008681514,0.000006202605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.079363,0.002104162,0.9044634,0.0008095075,0.0002137444,0.000160889,0.0003751739,0.006058668,0.006451387],"genre_scores_gemma":[0.8234681,0.0006194597,0.1645942,0.0009585212,0.0001038922,0.000215751,0.001585353,0.000371977,0.008082715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02475445,"threshold_uncertainty_score":0.04922068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0196459319324312,"score_gpt":0.2774523342760379,"score_spread":0.2578064023436067,"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."}}