{"id":"W3036116903","doi":"10.1162/tacl_a_00316","title":"Learning Lexical Subspaces in a Distributional Vector Space","year":2020,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Distributional semantics; Linear subspace; Artificial intelligence; Natural language processing; Similarity (geometry); Vector space; Word (group theory); Space (punctuation); Relation (database); Semantics (computer science); Semantic similarity; Suite; Code (set theory); Linguistics; Programming language; Data mining; 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":[0.001742265,0.001163298,0.00137806,0.002530649,0.0006995851,0.002564076,0.001369585,0.001162941,0.002647024],"category_scores_gemma":[0.005556089,0.0005251367,0.001159981,0.002495478,0.001075779,0.006074792,0.00312975,0.002018674,0.001638369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008138457,"about_ca_system_score_gemma":0.0009682217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00249283,"about_ca_topic_score_gemma":0.004119848,"domain_scores_codex":[0.9981315,0.0006467518,0.0001342734,0.0006417313,0.0003055115,0.0001403077],"domain_scores_gemma":[0.9980826,0.0008137062,0.000215071,0.0003656897,0.0003592963,0.0001635587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005051931,0.0005341108,0.01744426,0.0004795365,0.000311981,0.0003299372,0.001040102,0.1251475,0.009618644,0.1422143,0.01590299,0.6864715],"study_design_scores_gemma":[0.0000243788,0.0001350446,0.001144367,0.00005231711,0.00002130839,0.0001099053,0.0003257134,0.7769454,0.00122993,0.2157408,0.004236056,0.00003492108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05503278,0.0007160115,0.9394506,0.0004169782,0.00004822585,0.00007728327,0.0007656198,0.001693921,0.001798725],"genre_scores_gemma":[0.5963921,0.0008294194,0.3891634,0.0004788981,0.0001665555,0.0003450959,0.007380394,0.0004052473,0.004838897],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002647024,"threshold_uncertainty_score":0.009214044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01387567187832345,"score_gpt":0.2681135972948576,"score_spread":0.2542379254165342,"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."}}