{"id":"W2899501643","doi":"10.18653/v1/p19-1386","title":"The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Coreference; Computer science; Antecedent (behavioral psychology); Anaphora (linguistics); Benchmark (surveying); Natural language processing; Artificial intelligence; Task (project management); Context (archaeology); Feature (linguistics); Resolution (logic); Linguistics; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002711122,0.00008998525,0.00008835929,0.00001635378,0.0001850498,0.000195209,0.0003716482,0.00004184512,0.000008459711],"category_scores_gemma":[0.00003511349,0.00005791243,0.00002490154,0.00007522695,0.00002993363,0.0002626879,0.0001928005,0.00006960374,0.00002832483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003356964,"about_ca_system_score_gemma":0.00004477695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004402941,"about_ca_topic_score_gemma":0.00003843265,"domain_scores_codex":[0.9991341,0.00002649018,0.0001556166,0.000334133,0.0001192178,0.0002304095],"domain_scores_gemma":[0.9992684,0.000141585,0.00005845823,0.0003934323,0.00009272927,0.00004542003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003242826,0.00002840239,0.01764658,0.00004875859,0.00002051319,9.153297e-7,0.000976807,0.000273972,0.001554285,0.8190066,0.001766515,0.1586442],"study_design_scores_gemma":[0.0003586402,0.00005138979,0.02515947,0.0000198758,0.000004954251,0.00001963188,0.0002321572,0.9531018,0.0004213341,0.008179752,0.0122481,0.0002028923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2763208,0.0001666123,0.7173508,0.0002669527,0.0002845141,0.000351574,7.739592e-7,0.00008090775,0.00517711],"genre_scores_gemma":[0.9222705,0.00002341458,0.07523822,0.00009537111,0.00005484959,0.00002048005,0.000001099898,0.000005349997,0.002290673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9528278,"threshold_uncertainty_score":0.23616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03347918295935006,"score_gpt":0.2585531899851128,"score_spread":0.2250740070257628,"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."}}