{"id":"W3184956571","doi":"10.18653/v1/2021.sigdial-1.50","title":"Do Encoder Representations of Generative Dialogue Models have sufficient summary of the Information about the task ?","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Encoder; Transformer; Language model; Artificial intelligence; Representation (politics); Utterance; Generative grammar; Natural language processing; Task (project management); Generative model; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000234322,0.00005984296,0.00008952221,0.00003165107,0.0001012723,0.00005998037,0.0005276576,0.00002848273,0.00001366019],"category_scores_gemma":[0.00006977826,0.000033437,0.00007045591,0.0002407919,0.00005782077,0.0005512076,0.000378809,0.00007646681,0.000001728432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001685939,"about_ca_system_score_gemma":0.0001659892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002070387,"about_ca_topic_score_gemma":0.00009778678,"domain_scores_codex":[0.9990205,0.0001123544,0.0003306458,0.0001293889,0.0003084755,0.00009867947],"domain_scores_gemma":[0.9986508,0.00011495,0.0001420217,0.0007675717,0.0003059234,0.00001871762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.972852e-7,0.00003118728,0.0002816118,0.000008267733,0.00001489992,3.036193e-7,0.02048018,0.5019805,0.0007817538,0.472839,0.0008687365,0.002712519],"study_design_scores_gemma":[0.00009904462,0.000006053499,0.000630536,0.00001332604,0.000005381124,0.000002480398,0.001144223,0.9695034,0.01758914,0.01076809,0.0001917446,0.00004657649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0196697,0.0000933901,0.9613246,0.001729356,0.0002211519,0.0001536854,0.000009871613,0.00001375691,0.01678448],"genre_scores_gemma":[0.9768136,0.0000202348,0.02226484,0.0004395897,0.00001926902,0.00001254426,0.000005507031,0.000001794465,0.0004226263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9571439,"threshold_uncertainty_score":0.1363521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03447748161833202,"score_gpt":0.2667199454485412,"score_spread":0.2322424638302092,"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."}}