{"id":"W4255436026","doi":"10.24124/2018/58808","title":"Sentence encoders for semantic textual similarity: A survey.","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Sentence; Semantic similarity; Semantics (computer science); Task (project management); Similarity (geometry); Representation (politics); Focus (optics); Semantic role labeling; Encoder; Word (group theory); Distributional semantics; Deep learning; Linguistics; Programming language","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":[0.001290521,0.0009834152,0.000849446,0.002304294,0.0002670914,0.0009174034,0.001586636,0.0006929414,0.009351083],"category_scores_gemma":[0.00531526,0.0003736987,0.0007103708,0.001741366,0.000260604,0.003283681,0.0009192812,0.0009163137,0.005314319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983515,"about_ca_system_score_gemma":0.001057855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311754,"about_ca_topic_score_gemma":0.004094155,"domain_scores_codex":[0.9993991,0.0001627692,0.00006559858,0.0001458465,0.0001904321,0.00003622888],"domain_scores_gemma":[0.9986134,0.0006619701,0.0001054109,0.0002242311,0.0003345128,0.00006053961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001155463,0.0001741232,0.001181657,0.0009065501,0.0001015501,0.00009159447,0.00008573305,0.005033813,0.003554153,0.01081509,0.0405953,0.9373449],"study_design_scores_gemma":[0.0001084611,0.0007770638,0.008666161,0.001262387,0.0004600102,0.001790176,0.0004951793,0.690491,0.03001896,0.07575964,0.1900419,0.0001291531],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.04367115,0.1017595,0.7795475,0.002768477,0.001870358,0.0005779488,0.01215936,0.02516385,0.03248189],"genre_scores_gemma":[0.4160429,0.05784184,0.4464278,0.001853538,0.001690616,0.0009090925,0.04644471,0.00143186,0.02735765],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009351083,"threshold_uncertainty_score":0.03128248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04599552660613468,"score_gpt":0.3053835383355127,"score_spread":0.259388011729378,"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."}}