{"id":"W2377001998","doi":"","title":"Robust Character-Based Chinese Spoken Language Understanding with Domain Information","year":2010,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Robustness (evolution); Exploit; Natural language processing; Artificial intelligence; Spoken language; Language model; Character (mathematics); Test set; Speech recognition; Word (group theory); Domain (mathematical analysis); Set (abstract data type); Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008419549,0.0009933198,0.0008606046,0.0005845569,0.0002798028,0.0008678148,0.0009091755,0.0007076437,0.002162252],"category_scores_gemma":[0.002652983,0.0002847532,0.0004986816,0.0005825265,0.0003865554,0.00212666,0.001192569,0.0008428615,0.00140811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003454392,"about_ca_system_score_gemma":0.0007754239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00345264,"about_ca_topic_score_gemma":0.003414054,"domain_scores_codex":[0.9990149,0.0002464501,0.00007938692,0.0003798745,0.0001861124,0.00009320973],"domain_scores_gemma":[0.9984661,0.0006238943,0.0001089919,0.0003406555,0.0004099766,0.00005039723],"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":[0.0005618907,0.0001535154,0.001803022,0.0003320615,0.0001392702,0.0004477304,0.0007127097,0.07207589,0.2220088,0.002814776,0.002755224,0.6961952],"study_design_scores_gemma":[0.00002948558,0.0001614697,0.00207193,0.00001001436,0.00007251753,0.0001960208,0.0001880714,0.890098,0.1025565,0.002236928,0.002326596,0.00005238907],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.12248,0.0004078243,0.8690953,0.0001487108,0.00004199528,0.0001399564,0.0003239059,0.005006732,0.00235555],"genre_scores_gemma":[0.7373708,0.0002358133,0.2550978,0.0001332684,0.00003832085,0.0001753541,0.001827241,0.0002866154,0.004834748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00345264,"threshold_uncertainty_score":0.007233441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008692664868227845,"score_gpt":0.2299964082547704,"score_spread":0.2213037433865426,"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."}}