{"id":"W4393159548","doi":"10.1609/aaai.v38i12.29263","title":"Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"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":"Sentence; Natural language processing; Artificial intelligence; Computer science; Representation (politics); Unsupervised learning; Language model; Linguistics; Machine learning; Philosophy","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":[0.010861,0.001622486,0.001641102,0.001168981,0.0009732795,0.001992626,0.002250228,0.002049373,0.001525228],"category_scores_gemma":[0.05164589,0.0007202334,0.0009083318,0.0009391843,0.001383619,0.00812452,0.004919515,0.004367847,0.001128334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104933,"about_ca_system_score_gemma":0.001416221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001816603,"about_ca_topic_score_gemma":0.00340236,"domain_scores_codex":[0.9898784,0.005723671,0.0005120405,0.002281221,0.001282688,0.0003219961],"domain_scores_gemma":[0.9456508,0.04243835,0.001466344,0.0076957,0.00196508,0.0007836594],"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":[0.001523243,0.001957544,0.01323863,0.000758388,0.0003925555,0.0003505644,0.00200546,0.2181188,0.02290136,0.01483794,0.01071881,0.7131967],"study_design_scores_gemma":[0.00005918859,0.0004926202,0.002111769,0.00003532392,0.00003220496,0.0001245946,0.0002451566,0.9651412,0.01030192,0.01978524,0.001619212,0.0000515032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.368789,0.002009144,0.6142235,0.002132846,0.0001702641,0.0002897668,0.0006650152,0.006412254,0.005308186],"genre_scores_gemma":[0.818263,0.0003569668,0.1758433,0.0006319003,0.00009881634,0.0003080576,0.00236646,0.0006543619,0.001477182],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.010861,"threshold_uncertainty_score":0.05743921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09381631991397431,"score_gpt":0.3127379495608163,"score_spread":0.218921629646842,"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."}}