{"id":"W4283802608","doi":"10.1609/aaai.v36i10.21292","title":"ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Overfitting; Discriminative model; Computer science; Artificial intelligence; Natural language processing; Machine learning; Task (project management); Representation (politics); Feature learning; Regularization (linguistics); Class (philosophy); Pattern recognition (psychology); Artificial neural network","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":[0.002466222,0.001219351,0.001146922,0.001937242,0.0005743454,0.001085894,0.003122749,0.001832337,0.002066659],"category_scores_gemma":[0.006028606,0.0004347505,0.000998158,0.001115213,0.001115703,0.003153681,0.001818134,0.002677258,0.0009153821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001228996,"about_ca_system_score_gemma":0.0007209136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00210636,"about_ca_topic_score_gemma":0.003996678,"domain_scores_codex":[0.998983,0.0003422791,0.00004245272,0.0004070731,0.0001653326,0.00005997902],"domain_scores_gemma":[0.9980117,0.001157484,0.0001693475,0.0002802115,0.0002850373,0.00009616436],"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":[0.0006311301,0.0006541676,0.005424569,0.0004668237,0.0003258119,0.0003189946,0.000514699,0.2133077,0.01857899,0.03293346,0.01141851,0.7154252],"study_design_scores_gemma":[0.0000179962,0.0001211894,0.000436548,0.00002002027,0.00002312222,0.00006018097,0.00003155611,0.9724299,0.002952083,0.02156462,0.002328097,0.0000146985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01993942,0.000863248,0.9752128,0.0002810063,0.00008965711,0.0001466898,0.0003040139,0.001869766,0.001293432],"genre_scores_gemma":[0.4663683,0.0006576645,0.5222347,0.0007535798,0.0002652817,0.0005673189,0.002463763,0.0003965629,0.006292847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003122749,"threshold_uncertainty_score":0.01304275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1285249227605167,"score_gpt":0.3268101537159122,"score_spread":0.1982852309553954,"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."}}