{"id":"W2251262458","doi":"10.18653/v1/d13-1030","title":"Interpreting Anaphoric Shell Nouns using Antecedents of Cataphoric Shell Nouns as Training Data","year":2013,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Advanced Research Projects Agency; University of Toronto","keywords":"Noun; Computer science; Natural language processing; Shell (structure); Artificial intelligence; Baseline (sea); Nominalization; Training set; Obstacle; Natural (archaeology); Natural language; Range (aeronautics); Proper noun; History; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009346027,0.002293934,0.001244536,0.004576528,0.001908237,0.005686279,0.002041832,0.002767068,0.007365198],"category_scores_gemma":[0.04133713,0.001209708,0.001448221,0.002334295,0.001111104,0.007625485,0.003353034,0.003015968,0.0077928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008642878,"about_ca_system_score_gemma":0.002183476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004072404,"about_ca_topic_score_gemma":0.01085624,"domain_scores_codex":[0.9931116,0.002482538,0.0008209266,0.002302346,0.001040933,0.00024162],"domain_scores_gemma":[0.9532418,0.02919514,0.002931499,0.008132261,0.006024273,0.0004750502],"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":[0.001073068,0.0006800688,0.06070159,0.002334746,0.0005458595,0.0008098164,0.003912307,0.01145739,0.05920706,0.01486371,0.03175283,0.8126616],"study_design_scores_gemma":[0.000319884,0.0004994409,0.05843631,0.001523483,0.0006805155,0.003343897,0.006056514,0.439528,0.2219293,0.09871801,0.1685995,0.0003650696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.253855,0.003297522,0.6512447,0.002006898,0.0007938468,0.001046168,0.009406001,0.03938819,0.03896163],"genre_scores_gemma":[0.4156264,0.001130777,0.5525054,0.0005149464,0.0001822754,0.0002416836,0.02053027,0.001377038,0.007891103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009346027,"threshold_uncertainty_score":0.04942709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05275107700764495,"score_gpt":0.317283909282167,"score_spread":0.2645328322745221,"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."}}