{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002231588,0.001223674,0.0009705824,0.0009268629,0.0006068878,0.001229536,0.002120811,0.001378452,0.002270404],"category_scores_gemma":[0.007983832,0.000490346,0.0008503343,0.0005815771,0.001443794,0.003224033,0.002410583,0.00258044,0.001060462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000754029,"about_ca_system_score_gemma":0.0006535065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007969156,"about_ca_topic_score_gemma":0.001686405,"domain_scores_codex":[0.9987382,0.0005206384,0.00005683782,0.0003983258,0.000216817,0.00006921554],"domain_scores_gemma":[0.9969681,0.001777977,0.0002409127,0.0004091535,0.0004712092,0.0001326247],"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":[0.0008038707,0.0006250541,0.0050572,0.0003799173,0.0001746279,0.0004512347,0.0009279402,0.2350126,0.05185749,0.05842924,0.0122001,0.6340808],"study_design_scores_gemma":[0.00002459983,0.0001285058,0.000277333,0.00001309959,0.00001786904,0.00006810256,0.0000334768,0.9704515,0.005300311,0.02238057,0.001289797,0.00001475702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05549327,0.0002912526,0.9393824,0.0005845635,0.00007747587,0.0001256864,0.000169218,0.001398518,0.002477618],"genre_scores_gemma":[0.7077226,0.0002012113,0.2825104,0.0009395079,0.000201546,0.0004128829,0.001157455,0.0003273368,0.006526984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002270404,"threshold_uncertainty_score":0.0118019,"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."}}