{"id":"W4389519868","doi":"10.18653/v1/2023.findings-emnlp.199","title":"SimCKP: Simple Contrastive Learning of Keyphrase Representations","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Artificial intelligence; Natural language processing; Phrase; Generator (circuit theory); Context (archaeology); Benchmark (surveying); Margin (machine learning); Simple (philosophy); Set (abstract data type); Machine learning; Power (physics)","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":[0.00145116,0.001531179,0.001167265,0.001917711,0.0004187743,0.001229794,0.00251898,0.001439752,0.003616018],"category_scores_gemma":[0.004916759,0.000466259,0.001039884,0.001623179,0.0009285127,0.003108404,0.001703057,0.002242364,0.003132155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007658657,"about_ca_system_score_gemma":0.001135386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477314,"about_ca_topic_score_gemma":0.003504458,"domain_scores_codex":[0.999105,0.0001881351,0.00005541506,0.0003618204,0.0002135603,0.00007603805],"domain_scores_gemma":[0.9980567,0.0008985182,0.000175367,0.0004756374,0.0003042509,0.00008954902],"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":[0.0005296526,0.0003624992,0.002007619,0.0003860249,0.0001359193,0.0002225392,0.0001234875,0.06424048,0.03374673,0.00831237,0.01173022,0.8782025],"study_design_scores_gemma":[0.00007583491,0.0002911841,0.0007495286,0.00002396969,0.00005320901,0.0002059165,0.0000453081,0.9572226,0.01968144,0.01544315,0.00617388,0.00003401215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0219177,0.0008303027,0.9671283,0.0001584651,0.00009174242,0.0001931768,0.0005744768,0.007375241,0.001730551],"genre_scores_gemma":[0.3050204,0.0005493624,0.6817381,0.0003967953,0.0001784239,0.000408504,0.003989942,0.0006592836,0.007059179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003616018,"threshold_uncertainty_score":0.01209676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01824043602855783,"score_gpt":0.3299740072541026,"score_spread":0.3117335712255448,"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."}}