{"id":"W2788343755","doi":"10.1609/aaai.v32i1.11273","title":"CA-RNN: Using Context-Aligned Recurrent Neural Networks for Modeling Sentence Similarity","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Recurrent neural network; Computer science; Sentence; Benchmark (surveying); Context (archaeology); Artificial intelligence; Paraphrase; Natural language processing; Word (group theory); Similarity (geometry); Language model; Artificial neural network; Speech recognition","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007808937,0.0003243527,0.0003762262,0.0001179239,0.000493976,0.0003560415,0.002401253,0.0001450064,0.00001924347],"category_scores_gemma":[0.0004879066,0.0002640609,0.0001976027,0.0005213235,0.0003118891,0.0005973661,0.0005948251,0.0002711878,0.000009112234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009435174,"about_ca_system_score_gemma":0.0001151853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001244206,"about_ca_topic_score_gemma":0.00004631489,"domain_scores_codex":[0.9972126,0.00002765469,0.0008065407,0.0008231609,0.000500565,0.0006295045],"domain_scores_gemma":[0.9971613,0.0001110619,0.0004429567,0.000482567,0.001663422,0.0001386696],"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":[0.00020671,0.0002069985,0.0001844934,0.00008459151,0.00003530756,6.294221e-7,0.002369619,0.03259666,0.01841067,0.7598952,0.0001201115,0.185889],"study_design_scores_gemma":[0.00004148293,0.0001980594,0.000003305378,0.0002045603,0.00001669426,0.000005295264,0.0003774794,0.8828585,0.06436967,0.05165053,0.00001956853,0.0002548168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1671273,0.00002902243,0.8289269,0.001490047,0.001271566,0.0006163694,0.000005109649,0.00009213739,0.0004416029],"genre_scores_gemma":[0.9801481,0.00001207317,0.01893768,0.0004548721,0.0003674949,0.00002953051,5.605842e-7,0.0000184776,0.00003117821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8502619,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1788702740475964,"score_gpt":0.3348507905021531,"score_spread":0.1559805164545567,"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."}}