{"id":"W7126411529","doi":"10.18653/v1/2024.codi-1.11","title":"Exploring Soft-Label Training for Implicit Discourse Relation Recognition","year":2024,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Training (meteorology); Relation (database); Feature (linguistics); Action (physics); Interpretation (philosophy)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009368758,0.0002981684,0.0002601458,0.0002858894,0.0003414113,0.0009970074,0.0004131546,0.0001277542,0.00007727637],"category_scores_gemma":[0.0001289871,0.0003036317,0.0001751902,0.0005278034,0.00003945414,0.004253729,0.0001666334,0.0003277674,0.000180387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00016004,"about_ca_system_score_gemma":0.000243593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003547037,"about_ca_topic_score_gemma":0.00001399108,"domain_scores_codex":[0.9971692,0.00005359645,0.0006733987,0.001099669,0.0003439729,0.0006601536],"domain_scores_gemma":[0.9987279,0.0004102711,0.00008895327,0.0004908707,0.0001190473,0.0001630083],"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":[0.000008996154,0.00002662265,0.000004529968,0.0001605639,0.00003996121,0.000006692938,0.01253715,0.0006811076,0.0009087551,0.05982013,0.00008630811,0.9257192],"study_design_scores_gemma":[0.0003929474,0.0001360044,0.00004266027,0.0007126612,0.00006818095,0.00002369595,0.001221203,0.9614951,0.0005975756,0.03373503,0.001167628,0.0004073167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05463967,0.0005902968,0.9330306,0.003733454,0.004695334,0.0006256784,0.00001527486,0.0005413283,0.002128338],"genre_scores_gemma":[0.8301824,0.0001236594,0.1668149,0.0001599615,0.001190546,0.0002798468,0.00001816373,0.00004674736,0.001183772],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.960814,"threshold_uncertainty_score":0.9999416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3876095399079301,"score_gpt":0.3513438588791463,"score_spread":0.03626568102878375,"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."}}