{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006074695,0.0009733889,0.0005636063,0.001391598,0.0002951563,0.000819358,0.0008034115,0.001012127,0.002643764],"category_scores_gemma":[0.00248574,0.0002823793,0.000729995,0.001330282,0.0002782733,0.002021027,0.0005336583,0.0008412424,0.001320741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008720962,"about_ca_system_score_gemma":0.0005871744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007460216,"about_ca_topic_score_gemma":0.01195826,"domain_scores_codex":[0.9996532,0.0000630436,0.00002501197,0.0001531957,0.00005942108,0.00004607167],"domain_scores_gemma":[0.9993939,0.0002441723,0.00007308445,0.00006449901,0.0001828648,0.00004148869],"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":[0.0008658937,0.0005910674,0.01156789,0.0003525551,0.0004366125,0.0005343387,0.0002387867,0.1574218,0.05497075,0.006498992,0.01919241,0.747329],"study_design_scores_gemma":[0.000008611745,0.00003863085,0.001111761,0.000005717151,0.00002575933,0.00003918965,0.00001833974,0.992088,0.003468707,0.002693698,0.000494135,0.000007403505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4334337,0.002078936,0.542423,0.001152481,0.0005671842,0.0002317313,0.002822589,0.00832997,0.008960601],"genre_scores_gemma":[0.9091177,0.0003930874,0.08234031,0.0001907775,0.0002132855,0.00008977551,0.002781259,0.0001428277,0.004731058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007460216,"threshold_uncertainty_score":0.01483357,"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."}}