{"id":"W3118205297","doi":"10.18653/v1/2020.coling-main.455","title":"Intra-Correlation Encoding for Chinese Sentence Intention Matching","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Niagara; Brock University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Sentence; Natural language processing; Artificial intelligence; Encoding (memory); Ambiguity; Word (group theory); Matching (statistics); Embedding; Granularity; Feature (linguistics); Linguistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001400622,0.00006990868,0.00007515851,0.00002970777,0.00007465201,0.00009944045,0.0003041608,0.00002694946,0.000009624584],"category_scores_gemma":[0.0001063821,0.00005933897,0.00004613634,0.0001548089,0.000004971825,0.0006066791,0.00009995309,0.00007085444,0.00002219578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001883454,"about_ca_system_score_gemma":0.00001290474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002152848,"about_ca_topic_score_gemma":0.000004463541,"domain_scores_codex":[0.9993246,0.00001370696,0.0001667216,0.0002558899,0.0001121635,0.0001268859],"domain_scores_gemma":[0.9996483,0.00005677091,0.00004834348,0.0001423153,0.00004699541,0.00005721925],"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":[0.00002786607,0.00004981552,0.01496147,0.0001724849,0.00003108877,0.000007825627,0.01654923,0.04187535,0.0660098,0.6534839,0.0005757288,0.2062555],"study_design_scores_gemma":[0.0001354127,0.00001915133,0.0004347426,0.00001092481,0.000001551513,0.000002784949,0.00008142139,0.9864509,0.0004210953,0.01227184,0.00009462893,0.00007553992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04331101,0.00001073633,0.9499196,0.004582782,0.0003507117,0.0001452142,2.796493e-7,0.0002153652,0.001464292],"genre_scores_gemma":[0.8069547,0.000001621666,0.1920002,0.0008761599,0.00008910739,0.000007544935,0.000001479829,0.000003591822,0.00006565202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9445755,"threshold_uncertainty_score":0.2419773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02947500189495823,"score_gpt":0.2619573841806866,"score_spread":0.2324823822857284,"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."}}