{"id":"W2064641255","doi":"10.1109/isda.2010.5687037","title":"Pronominal anaphora understanding","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Anaphora (linguistics); Computer science; Covert; Argument (complex analysis); Natural language processing; Coreference; Parsing; Artificial intelligence; Set (abstract data type); Natural (archaeology); Natural language; Resolution (logic); Natural language understanding; Linguistics; Philosophy; Programming language; 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":[0.005150788,0.0005462044,0.0008081517,0.001780876,0.001601783,0.00634543,0.002490818,0.002000093,0.007391621],"category_scores_gemma":[0.0174832,0.0008657067,0.001015288,0.001439601,0.004504448,0.02057305,0.006559158,0.004586883,0.002079533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245442,"about_ca_system_score_gemma":0.001506758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001329462,"about_ca_topic_score_gemma":0.001305298,"domain_scores_codex":[0.9971214,0.0008127757,0.0002402316,0.0006605211,0.0009017062,0.0002632848],"domain_scores_gemma":[0.9864037,0.005916844,0.0009962959,0.005296695,0.001168599,0.0002178595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000474534,0.00005663305,0.002694246,0.0002279302,0.00003440689,0.0001333491,0.002276586,0.003259375,0.008567412,0.9062919,0.002476781,0.07393403],"study_design_scores_gemma":[0.000006410156,0.00001143702,0.0009555797,0.00005504569,0.00002913391,0.0002618179,0.0003210403,0.02169982,0.007348391,0.9543719,0.01491624,0.00002317019],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05535275,0.001330151,0.8572495,0.00549146,0.00009091382,0.00008431183,0.0004227738,0.001478514,0.07849962],"genre_scores_gemma":[0.774941,0.001001996,0.2128576,0.00137199,0.0001724086,0.00009006264,0.0006074804,0.0003060196,0.008651347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007391621,"threshold_uncertainty_score":0.02724028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229182958028818,"score_gpt":0.2700256137260089,"score_spread":0.2471073179231271,"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."}}