{"id":"W2963615308","doi":"10.1609/aaai.v33i01.3301232","title":"Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ranking (information retrieval); Social media; Relevance (law); Microblogging; Information retrieval; Convolutional neural network; Phrase; Artificial intelligence; Artificial neural network; Feature (linguistics); Matching (statistics); World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005725599,0.0002304847,0.0003203991,0.0001111399,0.0002329345,0.0002216351,0.001945317,0.0001039522,0.00002308699],"category_scores_gemma":[0.0003606007,0.0001661414,0.0001113218,0.0004064736,0.0002583783,0.0004228714,0.0003438341,0.0004649046,0.00005104546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009869122,"about_ca_system_score_gemma":0.0001860023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004211033,"about_ca_topic_score_gemma":0.00002643316,"domain_scores_codex":[0.9977745,0.00002209374,0.0004087082,0.0007158662,0.0006123757,0.0004664495],"domain_scores_gemma":[0.9979771,0.0003903917,0.0002355725,0.0002872923,0.001023715,0.00008595148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001334168,0.00008689519,0.0000937591,0.00004600252,0.00001668184,3.148934e-7,0.0109657,0.0002098503,0.03145722,0.9406487,0.00001269172,0.01632876],"study_design_scores_gemma":[0.0001974941,0.0003113011,0.0003258892,0.0003233021,0.00001449777,0.000007406434,0.00567353,0.3973298,0.2489766,0.3463446,0.00004634459,0.0004492489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4926648,0.00002075275,0.4942662,0.007618262,0.0005577222,0.001199718,0.0000103938,0.000143854,0.003518326],"genre_scores_gemma":[0.9473916,0.000006679099,0.05211529,0.00015781,0.0001088852,0.00003852195,3.518354e-7,0.00001788279,0.000163026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5943041,"threshold_uncertainty_score":0.6775049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1093619624775378,"score_gpt":0.3302808550666266,"score_spread":0.2209188925890888,"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."}}