Count, decompose and correct: A new approach to handwritten Chinese character error correction

Recently, handwritten Chinese character error correction has been greatly improved by employing encoder–decoder methods to decompose a Chinese character into an ideographic description sequence (IDS). However, existing methods implicitly capture and encode linguistic information inherent in IDS sequences, leading to a tendency to generate IDS sequences that match seen characters. This poses a challenge when dealing with an unseen misspelled character, as the decoder may generate an IDS sequence that matches a seen character instead. Therefore, we introduce Count, Decompose and Correct (CDC), a novel approach that exhibits better generalization towards unseen misspelled characters. CDC is mainly composed of three parts: the Counter, the Decomposer, and the Corrector. In the first stage, the Counter predicts the number of each radical class without the symbol-level position annotations. In the second stage, the Decomposer employs the counting information and generates the IDS sequence step by step. Moreover, by updating the counting information at each time step, the Decomposer becomes aware of the existence of each radical. With the decomposed IDS sequence, we can determine whether the given character is misspelled. If it is misspelled, the Corrector under the transductive transfer learning strategy predicts the ideal character that the user originally intended to write. We integrate our method into existing encoder–decoder models and significantly enhance their performance.