{"id":"W2115008472","doi":"10.1162/tacl_a_00233","title":"Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase","year":2013,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Paraphrase; Natural language processing; Similarity (geometry); Artificial intelligence; Computer science; Analogy; Distributional semantics; Word (group theory); Tuple; Pairwise comparison; Noun; Function (biology); Noun phrase; Semantic similarity; Linguistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004547349,0.0001704476,0.000343922,0.0001309132,0.0002228003,0.00006530731,0.0005201662,0.000218964,0.000004980509],"category_scores_gemma":[0.001183257,0.0001671154,0.000239561,0.0001944444,0.00006609494,0.00004492329,0.0001178689,0.0004025252,7.75291e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470503,"about_ca_system_score_gemma":0.0002902606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000565578,"about_ca_topic_score_gemma":0.000005997992,"domain_scores_codex":[0.9982619,0.0001169754,0.0006471943,0.000301221,0.0004980354,0.0001747319],"domain_scores_gemma":[0.995948,0.001182635,0.0008390858,0.000278256,0.001703799,0.00004820276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005641678,0.00007737151,0.003533009,0.0001809246,0.0001907401,9.234211e-8,0.0003559898,0.8270766,0.00001251374,0.1678716,0.00006916626,0.0006262732],"study_design_scores_gemma":[0.0003449974,0.0000291988,0.00348015,0.00006138639,0.0001198279,8.368723e-7,0.00002392214,0.8357258,0.00008851662,0.159591,0.0003953812,0.0001389886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01228212,0.0000973869,0.9849012,0.0005786795,0.001160313,0.0003747358,0.0004463468,0.00004049467,0.0001186586],"genre_scores_gemma":[0.8806467,0.00001996192,0.1188585,0.00002588593,0.0001161234,0.00002458863,0.0001465506,0.0000107461,0.0001509317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8683646,"threshold_uncertainty_score":0.681477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01650727852168584,"score_gpt":0.2569243560769647,"score_spread":0.2404170775552789,"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."}}