{"id":"W2576945865","doi":"","title":"The Importance of Discourse Context for Statistical Natural Language Generation","year":2004,"lang":"en","type":"article","venue":"Annual Meeting of the Special Interest Group on Discourse and Dialogue","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Realization (probability); Natural language generation; Natural language processing; Word (group theory); Word order; Natural language; Context (archaeology); Artificial intelligence; Natural (archaeology); Selection (genetic algorithm); Word lists by frequency; Linguistics; Statistics; Mathematics; History","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":[0.005680264,0.0007381309,0.001070707,0.002111325,0.00208573,0.004138185,0.0008082642,0.001406598,0.003475006],"category_scores_gemma":[0.05943943,0.0008097736,0.0005559042,0.00190686,0.002078083,0.009077953,0.003040561,0.002145792,0.0009091032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00076851,"about_ca_system_score_gemma":0.001109984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001188514,"about_ca_topic_score_gemma":0.002595722,"domain_scores_codex":[0.9927759,0.004717756,0.0003792612,0.001020147,0.0009013218,0.0002055591],"domain_scores_gemma":[0.9474277,0.04410516,0.001726662,0.003817701,0.002227585,0.0006951974],"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":[0.001233976,0.0002746866,0.0166717,0.001047408,0.0001520815,0.0007489878,0.003605868,0.0374435,0.03007521,0.3693848,0.003372492,0.5359893],"study_design_scores_gemma":[0.000136951,0.0003603083,0.00868271,0.0002955529,0.000194217,0.0006681973,0.001038758,0.2604675,0.01648236,0.6908447,0.02062492,0.0002038285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1639924,0.005634258,0.8092653,0.003154817,0.0003916575,0.0002257276,0.000443331,0.001658469,0.01523414],"genre_scores_gemma":[0.8260214,0.001134356,0.1707472,0.0002443975,0.000386161,0.0001599857,0.0002711836,0.0003349614,0.0007004293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005680264,"threshold_uncertainty_score":0.03004044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01965296451151733,"score_gpt":0.3155800113530325,"score_spread":0.2959270468415152,"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."}}