{"id":"W1794039122","doi":"10.1162/tacl_a_00080","title":"Learning to Understand Phrases by Embedding the Dictionary","year":2016,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada","keywords":"Computer science; Natural language processing; Word embedding; Artificial intelligence; Bridging (networking); Embedding; Lexical semantics; Semantics (computer science); Word (group theory); Task (project management); Linguistics; Lexical item","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005401591,0.0007588982,0.0003066454,0.0006497494,0.0002257549,0.0009960396,0.0008028085,0.0008797898,0.005467405],"category_scores_gemma":[0.003906179,0.0004331626,0.0006741954,0.000615159,0.0006714675,0.005583747,0.001356014,0.002013062,0.002377883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003700841,"about_ca_system_score_gemma":0.0004691446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001027856,"about_ca_topic_score_gemma":0.002093297,"domain_scores_codex":[0.9997166,0.00009447097,0.00001793562,0.0001195687,0.00003314924,0.00001832422],"domain_scores_gemma":[0.9989995,0.0006065253,0.00008055145,0.0001768279,0.0001063673,0.00003030793],"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":[0.0001902101,0.0001740433,0.004908606,0.0006160474,0.000144282,0.0003283462,0.001191937,0.08137792,0.02711996,0.08898593,0.01514849,0.7798142],"study_design_scores_gemma":[0.00002974928,0.0001241093,0.001132598,0.00009771817,0.00005069407,0.0002995711,0.0003863598,0.807824,0.009063927,0.1654742,0.01548609,0.00003097106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04986843,0.0004195559,0.9422755,0.0008810904,0.0001262456,0.00009159806,0.0006573438,0.001532428,0.004147825],"genre_scores_gemma":[0.5329585,0.0012617,0.4515588,0.0005519855,0.00012451,0.000252118,0.00347111,0.00041413,0.009407132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005467405,"threshold_uncertainty_score":0.01829034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01137076964757506,"score_gpt":0.2784432967756493,"score_spread":0.2670725271280742,"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."}}