{"id":"W2963047498","doi":"10.1109/tpami.2017.2695539","title":"Drawing and Recognizing Chinese Characters with Recurrent Neural Network","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":356,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Recurrent neural network; Computer science; Discriminative model; Artificial intelligence; Handwriting; Chinese characters; Generative grammar; Handwriting recognition; Convolutional neural network; Deep learning; Intelligent character recognition; Natural language processing; Generative model; Embedding; Task (project management); Pattern recognition (psychology); Machine learning; Speech recognition; Artificial neural network; Feature extraction; Character recognition; Image (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":[0.0002160073,0.0007824346,0.0005332553,0.0005364589,0.0002318289,0.0005067596,0.0008642405,0.0004344791,0.001935079],"category_scores_gemma":[0.0006813951,0.0003644063,0.0006909707,0.0007337788,0.0002505756,0.0008722973,0.0004312546,0.0006326842,0.0007423027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004772741,"about_ca_system_score_gemma":0.0004237298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009287333,"about_ca_topic_score_gemma":0.01154831,"domain_scores_codex":[0.9997327,0.00002974104,0.00001862143,0.0001019461,0.00008077094,0.00003620536],"domain_scores_gemma":[0.9998036,0.00004207437,0.0000329709,0.00004399792,0.00006023939,0.00001712799],"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":[0.000201204,0.0001164487,0.001409269,0.0001585373,0.00009786292,0.0004017012,0.0001069275,0.2018386,0.06180603,0.00392493,0.005812327,0.7241261],"study_design_scores_gemma":[0.000004753195,0.00003023193,0.0004449079,0.000004024628,0.00001450621,0.00005273613,0.000007400941,0.9885085,0.008852287,0.0009847475,0.001087176,0.000008656918],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08410576,0.000913714,0.9009354,0.0001863713,0.0001722441,0.00008846662,0.0003587073,0.008241815,0.004997583],"genre_scores_gemma":[0.6838607,0.0007750493,0.3033456,0.0001540921,0.00007728092,0.0001020534,0.001604431,0.0001713152,0.009909459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009287333,"threshold_uncertainty_score":0.01846653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02285943870308256,"score_gpt":0.2794097470582382,"score_spread":0.2565503083551556,"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."}}