{"id":"W4399426318","doi":"10.1162/tacl_a_00669","title":"Source-Free Domain Adaptation for Question Answering with Masked Self-training","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Question answering; Training (meteorology); Training set; Natural language processing; Artificial intelligence; Information retrieval; Speech recognition; Psychology","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":[0.0006295949,0.0001156597,0.0001399571,0.0001178218,0.0002954362,0.0001334556,0.0003817682,0.00007463119,7.56327e-7],"category_scores_gemma":[0.0004992173,0.0001020916,0.00014465,0.000300166,0.00001557799,0.0001211597,0.0000137615,0.000114937,8.780513e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002774742,"about_ca_system_score_gemma":0.0002645139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001705655,"about_ca_topic_score_gemma":0.00002794404,"domain_scores_codex":[0.9988038,0.00004584789,0.0003371657,0.0002485828,0.000386063,0.0001785457],"domain_scores_gemma":[0.997701,0.001091981,0.0002022992,0.000222808,0.000749401,0.00003247797],"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":[0.00001123584,0.0000257552,0.00007441994,0.00009052434,0.0001090713,8.660268e-8,0.002521168,0.7838908,0.00001688898,0.2106347,0.00004257671,0.002582807],"study_design_scores_gemma":[0.0004515818,0.00006911642,0.0002087723,0.00008386564,0.00007655966,0.00000205497,0.0001257744,0.878799,0.00006065821,0.113734,0.006277318,0.0001113324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001064854,0.00003423189,0.9957943,0.0008533779,0.001201762,0.0004863207,0.00007673656,0.0002742602,0.0002141487],"genre_scores_gemma":[0.5237089,9.520993e-7,0.4758142,0.00002472953,0.0001591187,0.00004809091,0.00001424991,0.00001329585,0.0002164037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5226441,"threshold_uncertainty_score":0.4163173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01946249239711238,"score_gpt":0.2532761076822381,"score_spread":0.2338136152851257,"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."}}