{"id":"W3115355887","doi":"10.18653/v1/2020.aacl-main.63","title":"Improving Context Modeling in Neural Topic Segmentation","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Western University","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Machine learning; Segmentation; Artificial neural network; Key (lock); Context (archaeology); Context model; Task (project management); Transfer of learning; German; Natural language processing","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":[0.0000617532,0.00005362973,0.00006701755,0.00002736721,0.00002281962,0.00006856863,0.0002595074,0.00001970137,0.00001076505],"category_scores_gemma":[0.00001981354,0.00005123316,0.00001815047,0.0001128039,0.000002664668,0.0004161671,0.0001186431,0.00007520722,0.00001169715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002194595,"about_ca_system_score_gemma":0.00001774087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002556262,"about_ca_topic_score_gemma":0.00004242862,"domain_scores_codex":[0.9993791,0.00001857929,0.0001567872,0.0002224658,0.00009806178,0.000125007],"domain_scores_gemma":[0.9997789,0.00001248321,0.00002002781,0.0001269461,0.00001525124,0.00004634682],"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":[0.000002788665,0.000009719298,0.00142876,0.00001911041,0.000002122753,0.00001144841,0.00381382,0.130656,0.005782248,0.0150937,0.00001605424,0.8431642],"study_design_scores_gemma":[0.0002011298,0.00001340244,0.00002607372,0.000002399773,4.681758e-7,8.282405e-7,0.0001778092,0.9986135,0.0006650442,0.0002321697,0.000008313228,0.00005881823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2025654,0.0000400937,0.7941257,0.002644423,0.00008426479,0.00006768928,5.201071e-8,0.00008372603,0.0003886269],"genre_scores_gemma":[0.9420093,8.116309e-7,0.05536421,0.002547528,0.00004450147,0.000003935005,3.26714e-7,0.000002598236,0.00002681503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8679575,"threshold_uncertainty_score":0.2089228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06253534279808755,"score_gpt":0.253566698615409,"score_spread":0.1910313558173214,"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."}}