{"id":"W4389520117","doi":"10.18653/v1/2023.findings-emnlp.6","title":"Time-Aware Representation Learning for Time-Sensitive Question Answering","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Context (archaeology); Task (project management); Question answering; Sentence; Metric (unit); Baseline (sea); Artificial intelligence; Natural language processing; Language model; Representation (politics); Context model; Code (set theory); Information retrieval; Machine learning; Programming language","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":[0.001750898,0.001203122,0.0008822432,0.001669121,0.0004021884,0.001110012,0.001891904,0.001725462,0.003775738],"category_scores_gemma":[0.007810219,0.0003796541,0.001572676,0.001521041,0.0003793538,0.003518428,0.001642677,0.002423143,0.002328178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001179875,"about_ca_system_score_gemma":0.0011088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004668177,"about_ca_topic_score_gemma":0.005278531,"domain_scores_codex":[0.9987178,0.0003964429,0.00008851118,0.0005112317,0.0001614314,0.0001247087],"domain_scores_gemma":[0.9971967,0.001699902,0.0001724462,0.000479329,0.0003406126,0.0001110289],"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":[0.0004826592,0.0007071536,0.004167639,0.000487166,0.000163756,0.0002134306,0.0007114381,0.09415574,0.02141881,0.01158431,0.0404254,0.8254824],"study_design_scores_gemma":[0.00004713421,0.0001447202,0.001003295,0.00003621807,0.00005553121,0.0001140382,0.0001212763,0.9559314,0.006121523,0.02900988,0.007387558,0.00002738125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06230294,0.002496917,0.9124359,0.001035018,0.0002976084,0.0002573036,0.003560988,0.01482053,0.002792807],"genre_scores_gemma":[0.6158236,0.001148026,0.3544211,0.0007957538,0.000443984,0.0006660993,0.02050469,0.0005716378,0.005625015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004668177,"threshold_uncertainty_score":0.01263112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02731351606708088,"score_gpt":0.2972946109753773,"score_spread":0.2699810949082964,"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."}}