{"id":"W4283797513","doi":"10.1609/aaai.v36i10.21428","title":"Unsupervised Sentence Representation via Contrastive Learning with Mixing Negatives","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":53,"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; Leverhulme Trust","keywords":"Computer science; Sentence; Artificial intelligence; Representation (politics); Natural language processing; Task (project management); Feature learning; Similarity (geometry); Transfer of learning; Unsupervised learning; Process (computing); Machine learning; Pattern recognition (psychology); Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0004947057,0.0001963234,0.0002338409,0.0001273786,0.0006157458,0.0001888728,0.00161663,0.00003196995,0.00007032232],"category_scores_gemma":[0.0002762026,0.0001536325,0.00007636211,0.0008589944,0.0001965783,0.0005391408,0.0006294797,0.0005368703,0.00001078699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007907002,"about_ca_system_score_gemma":0.0001004198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001139161,"about_ca_topic_score_gemma":0.000006416771,"domain_scores_codex":[0.9978266,0.00006643763,0.0004279375,0.0006110361,0.0007438806,0.0003240622],"domain_scores_gemma":[0.9985706,0.0001611244,0.0004247969,0.0002550072,0.0005205969,0.00006786314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002413519,0.000196065,0.003694778,0.00003682354,0.00004765828,0.000003809227,0.01531396,0.02040512,0.1303152,0.713191,0.00002000177,0.1165341],"study_design_scores_gemma":[0.00006230696,0.0003672198,0.0003812729,0.0001042583,0.00001205177,0.00001690252,0.006928012,0.6711004,0.2679369,0.05282044,0.00002870178,0.0002414655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4281442,0.00002101618,0.5625069,0.003423805,0.0003057297,0.0005741408,0.000002291622,0.0001593133,0.00486262],"genre_scores_gemma":[0.99267,0.000006950136,0.006852685,0.000153828,0.0000362632,0.00006929997,5.515235e-7,0.00001199115,0.0001984466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6603706,"threshold_uncertainty_score":0.626495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06820739762611006,"score_gpt":0.2824664433663063,"score_spread":0.2142590457401963,"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."}}