{"id":"W2898487021","doi":"10.48550/arxiv.1810.10641","title":"Predicting the Semantic Textual Similarity with Siamese CNN and LSTM","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Natural language processing; Semantic similarity; Similarity (geometry); Artificial intelligence; Context (archaeology); Convolution (computer science); Convolutional neural network; Recurrent neural network; Artificial neural network; Image (mathematics)","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":[0.0003752557,0.0002650918,0.0002399945,0.0001044759,0.0003128618,0.0002035746,0.001574167,0.0001889888,0.00001033052],"category_scores_gemma":[0.00004126945,0.0002097418,0.00006882592,0.0002856819,0.0002620158,0.0002976251,0.002790751,0.000637773,0.00001491809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007362953,"about_ca_system_score_gemma":0.0001682563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002668398,"about_ca_topic_score_gemma":0.000160661,"domain_scores_codex":[0.9982066,0.0001332804,0.0001491682,0.001053657,0.0001256928,0.000331637],"domain_scores_gemma":[0.9980265,0.0001403475,0.0001869751,0.001392266,0.0001307447,0.000123182],"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":[0.0001452993,0.0002704269,0.3258969,0.0006371599,0.0007180463,0.001365257,0.008790703,0.3635168,0.00004583195,0.2922814,0.0007178164,0.005614344],"study_design_scores_gemma":[0.0002791301,0.00006021559,0.004096081,0.0001254043,0.00006866999,0.00001818314,0.0001878836,0.9828331,0.00002305222,0.01184369,0.0001751494,0.0002894232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4946472,0.00002983419,0.5031146,0.0002576149,0.0001450078,0.0001861054,0.000002962265,0.0001432559,0.001473366],"genre_scores_gemma":[0.996069,0.00004218124,0.002952374,0.0001841779,0.000147791,6.669291e-7,0.000001952433,0.00001317349,0.0005886538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6193163,"threshold_uncertainty_score":0.8553022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05907066756665994,"score_gpt":0.1795122617828892,"score_spread":0.1204415942162292,"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."}}