{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009736823,0.0001751708,0.0002410126,0.0000544341,0.0003128236,0.0003542925,0.0007495556,0.00006266684,0.000003449988],"category_scores_gemma":[0.00003508926,0.0001317421,0.00007002099,0.000112395,0.00001565802,0.0006853524,0.0004817783,0.0002556874,0.00001041856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003242346,"about_ca_system_score_gemma":0.00003325332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001800006,"about_ca_topic_score_gemma":0.00002288074,"domain_scores_codex":[0.9983892,0.00004309104,0.0003242963,0.0005700914,0.0002663405,0.0004069109],"domain_scores_gemma":[0.9987384,0.0003917711,0.00005157386,0.0006972101,0.00005234147,0.00006871974],"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":[0.00001157706,0.00003027521,0.01485274,0.0004695557,0.0001013205,0.000005520935,0.007160555,0.5403447,0.004272106,0.1991528,0.0001014431,0.2334974],"study_design_scores_gemma":[0.0001244123,0.00001121108,0.0002401445,0.00006974909,0.00001001494,0.000008212392,0.0001105048,0.9449044,0.0001924845,0.05409151,0.0000523072,0.000185041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4139906,0.00006796129,0.5836299,0.001403449,0.0001278025,0.0002743706,0.000001010899,0.0001166498,0.0003882253],"genre_scores_gemma":[0.8796276,0.00001144722,0.119502,0.0004874919,0.0001553067,0.00001050713,0.000001129641,0.00001657964,0.0001878993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.465637,"threshold_uncertainty_score":0.5372287,"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."}}