{"id":"W3181113307","doi":"10.18653/v1/2022.acl-long.87","title":"LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substitution (logic); Computer science; Natural language processing; Artificial intelligence; Embedding; Context (archaeology); Sentence; Word (group theory); Task (project management); Similarity (geometry); Benchmark (surveying); Lexical item; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001874411,0.0002416645,0.0003912439,0.0001182999,0.001271178,0.0001624299,0.00194751,0.0001394362,0.000002927553],"category_scores_gemma":[0.02028711,0.000192445,0.0003825802,0.0005625745,0.0001617151,0.0001599764,0.001003325,0.0004564443,6.192972e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005631122,"about_ca_system_score_gemma":0.0002146933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009966701,"about_ca_topic_score_gemma":0.00001470685,"domain_scores_codex":[0.9974164,0.00006346318,0.000789534,0.0004751173,0.0009147067,0.0003407917],"domain_scores_gemma":[0.9932634,0.001689906,0.001774748,0.0001742966,0.003032047,0.00006555369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003536216,0.0004057291,0.03377095,0.0004893822,0.000318623,3.661758e-7,0.01877588,0.006844467,0.006892745,0.9208363,0.008248452,0.003063434],"study_design_scores_gemma":[0.002614175,0.0007539616,0.006386431,0.0009558634,0.0003897917,0.000009085611,0.003442806,0.3626685,0.02504149,0.5501336,0.04648246,0.001121805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7298847,0.004417379,0.2174641,0.01209558,0.01301396,0.007562714,0.002656514,0.001886255,0.01101886],"genre_scores_gemma":[0.884102,7.011619e-7,0.1146156,0.0002006221,0.000477588,0.00008944268,0.00002708512,0.00002434918,0.0004625987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3707027,"threshold_uncertainty_score":0.9879654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009318653360598592,"score_gpt":0.2633825578358897,"score_spread":0.254063904475291,"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."}}