{"id":"W4320082227","doi":"10.53482/2022_53_402","title":"Quantifying syntax similarity with a polynomial representation of dependency trees","year":2022,"lang":"en","type":"article","venue":"Glottometrics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Government of Canada; Australian Government; National Science Foundation","keywords":"Dependency (UML); Syntax; Computer science; Abstract syntax tree; Natural language processing; Artificial intelligence; Abstract syntax; Representation (politics); Graph; Word grammar; Sentence; Dependency graph; Similarity (geometry); Theoretical computer science; Generative grammar; Relational grammar; Emergent grammar","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":[0.001956124,0.0005778022,0.000626281,0.007418152,0.0007510079,0.002068496,0.001083206,0.0008205292,0.003125432],"category_scores_gemma":[0.01495954,0.0002837113,0.0008990523,0.008148298,0.001736716,0.004927348,0.001495195,0.001054339,0.0007598255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001498315,"about_ca_system_score_gemma":0.00130844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003609201,"about_ca_topic_score_gemma":0.003123451,"domain_scores_codex":[0.9979101,0.0006278269,0.0001558712,0.0004606422,0.0006559183,0.0001895802],"domain_scores_gemma":[0.9917548,0.004345421,0.001379641,0.001399778,0.0008687452,0.0002516632],"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":[0.0002864548,0.0002497071,0.01454959,0.0004212538,0.0001299903,0.000358424,0.001366628,0.1883688,0.03063406,0.5037256,0.005871046,0.2540385],"study_design_scores_gemma":[0.00002128804,0.0001004278,0.00870621,0.00003835148,0.00003855615,0.0002950326,0.0002729018,0.6646866,0.005836996,0.3136607,0.006259696,0.00008323167],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05882544,0.0002056651,0.9356467,0.0001815032,0.00002429387,0.00008727042,0.0008770708,0.000888809,0.003263318],"genre_scores_gemma":[0.6999678,0.0003212113,0.2952383,0.0001039765,0.00009104233,0.0002272615,0.00194181,0.000394673,0.001713953],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007418152,"threshold_uncertainty_score":0.01087105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04253292317678645,"score_gpt":0.3129962674554597,"score_spread":0.2704633442786732,"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."}}