{"id":"W3115586753","doi":"10.18653/v1/2020.coling-main.520","title":"A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Research Foundation Singapore; National Research Foundation","keywords":"Computer science; Focus (optics); Benchmark (surveying); Graph; Artificial intelligence; Attention network; Task (project management); Natural language processing; Theoretical computer science","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":[0.0005871156,0.001211814,0.0008479042,0.00113489,0.0007014143,0.0005563975,0.001667635,0.001222286,0.003617271],"category_scores_gemma":[0.001701913,0.0004055833,0.0007497025,0.001826856,0.0004813225,0.002034383,0.001675242,0.001443515,0.001177895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009118171,"about_ca_system_score_gemma":0.001205722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01480181,"about_ca_topic_score_gemma":0.03320044,"domain_scores_codex":[0.9995219,0.00008608111,0.00001823872,0.0002362523,0.00006648288,0.00007106527],"domain_scores_gemma":[0.9996011,0.0001070921,0.00004706621,0.00009900255,0.0001123888,0.00003339289],"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":[0.0003440823,0.0003137001,0.004753889,0.0002724476,0.0002751267,0.0003634578,0.0002136118,0.1665826,0.01831159,0.01304676,0.03166243,0.7638603],"study_design_scores_gemma":[0.00002305696,0.00006916564,0.001319718,0.00002215179,0.0000890694,0.0001279872,0.00005471364,0.9776225,0.004221621,0.009780214,0.006649987,0.00001980567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0867362,0.003698407,0.8878764,0.0008393438,0.0005597192,0.0001762785,0.001256827,0.009076349,0.009780485],"genre_scores_gemma":[0.716208,0.001361646,0.2556877,0.00121937,0.0002602071,0.0002076668,0.007433894,0.0005688228,0.01705266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01480181,"threshold_uncertainty_score":0.02943128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02634194474832662,"score_gpt":0.305094850623061,"score_spread":0.2787529058747343,"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."}}