{"id":"W4200584900","doi":"10.1145/3426971","title":"SANTM: Efficient Self-attention-driven Network for Text Matching","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Business Finland; Academy of Finland","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Matching (statistics); Pooling; Inference; Question answering; Natural language processing; Paraphrase; Task (project management); Sentence; Benchmark (surveying); Machine learning","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":[0.0009935498,0.0009776601,0.001005574,0.001484543,0.0005712057,0.0007708641,0.003215642,0.002050372,0.004956938],"category_scores_gemma":[0.003951554,0.0006118585,0.0009713161,0.001267764,0.0005676911,0.002759805,0.001662529,0.001578828,0.002049744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001717588,"about_ca_system_score_gemma":0.001300487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007650934,"about_ca_topic_score_gemma":0.01305033,"domain_scores_codex":[0.9995597,0.00009045187,0.00002516435,0.0001754633,0.00009597116,0.00005333898],"domain_scores_gemma":[0.9992167,0.000364681,0.00007059808,0.000141226,0.0001591342,0.00004761772],"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":[0.0005653247,0.0004668181,0.002549925,0.0003812942,0.0001796855,0.0002827872,0.0002692557,0.3317346,0.0171003,0.02118518,0.03703572,0.5882491],"study_design_scores_gemma":[0.00001562918,0.00002648683,0.00012958,0.000005335691,0.00001297011,0.00002885567,0.000009485193,0.9891382,0.001984467,0.007152733,0.001490332,0.000005816592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04522455,0.001377804,0.9312022,0.0009093332,0.0002926883,0.0003747446,0.00247793,0.01250618,0.005634625],"genre_scores_gemma":[0.5635204,0.0008133158,0.4020627,0.001308214,0.0003543378,0.0007695701,0.009297035,0.000782723,0.02109175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007650934,"threshold_uncertainty_score":0.01658261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01323042347980237,"score_gpt":0.2498152077177358,"score_spread":0.2365847842379334,"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."}}