{"id":"W2984469754","doi":"10.18653/v1/d19-1540","title":"Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bridging (networking); Computer science; Natural language processing; Relevance (law); Matching (statistics); Similarity (geometry); Semantic similarity; Artificial intelligence; Semantic matching; Natural language; Information retrieval; Mathematics; Image (mathematics)","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":[0.007845947,0.0008192507,0.002024487,0.004909308,0.001289581,0.003263999,0.002140867,0.002613018,0.003152575],"category_scores_gemma":[0.02830907,0.0005592899,0.001631545,0.004810122,0.001429915,0.01183958,0.004581454,0.001948658,0.001747194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009652182,"about_ca_system_score_gemma":0.001882787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089031,"about_ca_topic_score_gemma":0.003412378,"domain_scores_codex":[0.9907301,0.004534072,0.0008604709,0.001637195,0.001846851,0.0003913621],"domain_scores_gemma":[0.9864342,0.008627483,0.0005681546,0.002504996,0.001511963,0.0003531316],"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":[0.001096192,0.0006046382,0.004810032,0.001148153,0.0004462983,0.0002854461,0.001285772,0.02638025,0.01141952,0.1089318,0.01706446,0.8265274],"study_design_scores_gemma":[0.0001037264,0.0003314976,0.002746242,0.0001634564,0.0002296412,0.0003840628,0.0005204577,0.7163407,0.006782334,0.254377,0.01792882,0.00009203469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03484139,0.006938775,0.9524018,0.001087304,0.0002824907,0.0002150708,0.0004273216,0.001040849,0.002765099],"genre_scores_gemma":[0.6070431,0.00376886,0.3816636,0.0005938861,0.0009654065,0.0004555263,0.002325588,0.000379535,0.002804539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007845947,"threshold_uncertainty_score":0.04149383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04279903629725576,"score_gpt":0.2781462756295075,"score_spread":0.2353472393322517,"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."}}