{"id":"W4413060628","doi":"10.1145/3748316","title":"Inner-character and Inner-word Features Based Representation Learning for Chinese Word Embedding","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Natural Science Foundation of Sichuan Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Pinyin; Computer science; Artificial intelligence; Natural language processing; Word (group theory); Character (mathematics); Word embedding; Feature (linguistics); Similarity (geometry); Chinese characters; Speech recognition; Embedding; 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":[0.0002463104,0.0001758069,0.0001649278,0.0004629463,0.0005605098,0.0006799541,0.0002569303,0.00010439,0.00000750345],"category_scores_gemma":[0.0001780941,0.000160089,0.00004872849,0.0004966844,0.00003379295,0.001771854,0.00002238303,0.0003044301,0.000001711103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003418254,"about_ca_system_score_gemma":0.00005098546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001519629,"about_ca_topic_score_gemma":0.00001015707,"domain_scores_codex":[0.9989762,0.00004636529,0.0003346815,0.0002548822,0.0001726457,0.0002152076],"domain_scores_gemma":[0.9992488,0.000151813,0.0001534028,0.0003020885,0.00007688363,0.00006701644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003763684,0.0000158348,0.000132239,0.0002294412,0.00001117569,8.451866e-7,0.01269745,0.009403499,0.0002311088,0.0001005295,0.00001802137,0.9771222],"study_design_scores_gemma":[0.001640206,0.00004540207,0.004228877,0.0005468004,0.00003100529,0.00001879864,0.007666362,0.9793787,0.002168478,0.0004871892,0.003422219,0.0003659464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08615807,0.0001158162,0.9098367,0.002483874,0.00007921662,0.0002615328,0.000002935097,0.0002144469,0.0008474075],"genre_scores_gemma":[0.9546114,0.000005558942,0.04340715,0.001473248,0.00003630748,0.00005391401,0.00002814532,0.000008864467,0.0003753612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9767563,"threshold_uncertainty_score":0.6556813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006695338832000711,"score_gpt":0.2708147697501971,"score_spread":0.2641194309181965,"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."}}