{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000772108,0.0007878011,0.0006094397,0.002049672,0.000337739,0.0005716961,0.0008315955,0.0004563235,0.00310213],"category_scores_gemma":[0.002771802,0.0002004206,0.0008331374,0.001968209,0.00029214,0.001772066,0.0007883898,0.000827624,0.001441741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007034014,"about_ca_system_score_gemma":0.001349729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009267111,"about_ca_topic_score_gemma":0.01070837,"domain_scores_codex":[0.9994318,0.0001401937,0.00006039862,0.0001622386,0.0001321079,0.00007327285],"domain_scores_gemma":[0.9992009,0.0002345126,0.00009330128,0.0001460619,0.0002810397,0.00004430908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005671337,0.0003512249,0.006440041,0.0003407615,0.0001116235,0.0002624614,0.0005691582,0.03341783,0.0215566,0.01423864,0.02360392,0.8985405],"study_design_scores_gemma":[0.00003670974,0.0001606619,0.004448393,0.00003609077,0.0001011686,0.0001641884,0.0001367034,0.9600548,0.01298889,0.01301902,0.008807545,0.00004586509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09823643,0.001991235,0.8820794,0.0005115861,0.0002318064,0.0003386246,0.002576562,0.007221402,0.00681295],"genre_scores_gemma":[0.7630703,0.00086863,0.2209518,0.0002955411,0.0002012292,0.0004538199,0.006405489,0.0004168718,0.00733631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009267111,"threshold_uncertainty_score":0.01842636,"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."}}