{"id":"W7132934590","doi":"","title":"Subcategorial Considerations in Statistical Categorial Parsing","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Combinatory categorial grammar; Categorial grammar; Parsing; Rule-based machine translation; Link grammar; Natural language; Statistical learning; Grammar","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":[0.006005517,0.000634676,0.0006860508,0.001684046,0.001027266,0.003826383,0.001744829,0.001960817,0.003700927],"category_scores_gemma":[0.02081897,0.0007770227,0.001334565,0.001199015,0.005608592,0.01055576,0.003369556,0.005444821,0.0007752621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001869919,"about_ca_system_score_gemma":0.001495036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002187989,"about_ca_topic_score_gemma":0.003096822,"domain_scores_codex":[0.996823,0.001456074,0.0002200272,0.0006695301,0.0006298612,0.0002016114],"domain_scores_gemma":[0.9877411,0.00913092,0.0004546313,0.001674897,0.0008089864,0.0001896176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001277597,0.000008392294,0.000610008,0.00004506379,0.0000123321,0.0001014892,0.0003662214,0.01651694,0.000790054,0.9558184,0.0009326688,0.0247857],"study_design_scores_gemma":[0.00000158634,0.000005299482,0.0001168173,0.00001853745,0.000005433797,0.00003997096,0.00004046542,0.04206115,0.0003560358,0.955201,0.0021457,0.000007916019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01606603,0.0008016192,0.9681265,0.003460639,0.0001299537,0.00003473724,0.0000798438,0.0003497328,0.01095087],"genre_scores_gemma":[0.6012472,0.001542958,0.3865144,0.002017861,0.0005400511,0.0002067032,0.0003200787,0.0006220089,0.00698874],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006005517,"threshold_uncertainty_score":0.03176057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02561535006652994,"score_gpt":0.3742374172771301,"score_spread":0.3486220672106002,"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."}}