{"id":"W2398787226","doi":"","title":"A Neurally Plausible Encoding of Word Order Information into a Semantic Vector Space","year":2013,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Encoding (memory); Word (group theory); Computer science; Natural language processing; Semantics (computer science); Distributional semantics; Vector space; Artificial intelligence; Word order; Space (punctuation); Vector space model; Theoretical computer science; Semantic similarity; 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":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0001271726,0.0002368553,0.0002519747,0.0002641031,0.00009926926,0.002178852,0.001075678,0.000108473,0.0001949034],"category_scores_gemma":[0.0002812817,0.0002159287,0.00009787952,0.0008512217,0.00004251283,0.02338695,0.0006576848,0.0002994989,0.001833339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002918862,"about_ca_system_score_gemma":0.0001542848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002804761,"about_ca_topic_score_gemma":0.000001336836,"domain_scores_codex":[0.9982245,0.00004622051,0.0005717696,0.0003168656,0.0004409937,0.0003996791],"domain_scores_gemma":[0.9988005,0.0001200072,0.000220477,0.0005314611,0.0001143894,0.0002131404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001190949,0.0005824801,0.3447697,0.001481876,0.0002185426,0.00004581159,0.003552266,0.002832907,0.007093137,0.29982,0.008537401,0.3309468],"study_design_scores_gemma":[0.003853771,0.0006347187,0.05016792,0.001322646,0.00005117309,0.000131093,0.0004112819,0.4957964,0.04428933,0.2555482,0.1441593,0.003634203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.801433,0.00005376309,0.1867367,0.002398273,0.0002109264,0.0004906165,0.00004475916,0.0005534403,0.008078542],"genre_scores_gemma":[0.944419,0.000003789326,0.05469228,0.0005340024,0.00005113871,0.00002590376,0.00003645277,0.00002093946,0.0002164802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4929635,"threshold_uncertainty_score":0.9989439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126613636147259,"score_gpt":0.2010629179726693,"score_spread":0.1897967816111967,"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."}}