{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007595406,0.001910971,0.001091078,0.002284803,0.0007400781,0.002159582,0.001840887,0.001124366,0.01672475],"category_scores_gemma":[0.003663172,0.0007346359,0.001269709,0.001998828,0.0007002108,0.005926107,0.00419085,0.001369683,0.007814658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007518679,"about_ca_system_score_gemma":0.001563656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005463846,"about_ca_topic_score_gemma":0.01753638,"domain_scores_codex":[0.9990947,0.0002297333,0.00008375481,0.0003034546,0.0002024325,0.00008593682],"domain_scores_gemma":[0.999064,0.0003387038,0.00004509649,0.0003135489,0.0001898557,0.00004874345],"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":[0.0006112101,0.0005180213,0.004322423,0.0008011962,0.0002829784,0.0007899771,0.0004770539,0.0182329,0.01115702,0.02487601,0.1009018,0.8370295],"study_design_scores_gemma":[0.0002150472,0.0002978081,0.002443293,0.0002129517,0.0002450315,0.0007545163,0.0007324844,0.7508488,0.02245549,0.1259713,0.09568084,0.0001424293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05192531,0.001867719,0.823733,0.0009770328,0.0005650847,0.0006745696,0.01249112,0.0867079,0.02105833],"genre_scores_gemma":[0.2234212,0.00104872,0.7192078,0.0007895234,0.0001945412,0.0007760142,0.03759424,0.005340398,0.01162739],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01672475,"threshold_uncertainty_score":0.05594981,"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."}}