{"id":"W4312301825","doi":"10.1109/saci55618.2022.9919604","title":"A Deep Learning Method for Sentence Embeddings Based on Hadamard Matrix Encodings","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Sentence; Parsing; Embedding; Word embedding; Dependency grammar; Word (group theory); Natural language processing; Deep learning; String (physics); Dependency (UML); Artificial neural network; Convolutional neural network; 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":[0.0008455713,0.001187676,0.000637869,0.001344492,0.0003945478,0.001016501,0.001314094,0.001007661,0.006506596],"category_scores_gemma":[0.003467072,0.0005315684,0.0009326671,0.001226452,0.0004789623,0.003223091,0.001313322,0.00243834,0.002901892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006926849,"about_ca_system_score_gemma":0.0009617906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002638785,"about_ca_topic_score_gemma":0.00480304,"domain_scores_codex":[0.9993594,0.0001734242,0.00006788248,0.0001786595,0.0001696519,0.00005088922],"domain_scores_gemma":[0.9990828,0.0003634845,0.00007777406,0.0001561349,0.0002711414,0.00004861674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002583272,0.0001670884,0.0007571913,0.000282367,0.0001275873,0.0002260404,0.0002129135,0.06444659,0.02004553,0.04855286,0.02232543,0.8425981],"study_design_scores_gemma":[0.00002637796,0.000104295,0.0002655681,0.00003431333,0.00002814141,0.0001375839,0.00004354427,0.9421239,0.01032464,0.03746407,0.009417285,0.00003027743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004988075,0.0002647694,0.9898913,0.0001974722,0.0001599145,0.00006237344,0.0005410975,0.003028112,0.000866909],"genre_scores_gemma":[0.135676,0.0004490407,0.8501567,0.0002379015,0.0001966666,0.0002854948,0.004214754,0.0005934749,0.008189891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006506596,"threshold_uncertainty_score":0.02176672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01180729227690377,"score_gpt":0.3144126664529631,"score_spread":0.3026053741760593,"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."}}