Chinese spelling correction has achieved significant progress, but critical challenges remain, especially in handling visually and phonetically similar errors within complex syntactic structures. This paper introduces a novel approach combining a Long Short-Term Memory Network (LSTM)-enhanced Transformer for error detection and Bidirectional Encoder Representations from Transformers (BERT)-based correction with a dynamic adaptive weighting scheme. Transformer uses global attention mechanism to capture dependencies between any two positions in the input sequence. By processing each token in the sequence recursively, LSTM is able to more finely capture local context and sequential information within the sequence. Based on adaptive weighting coefficient, weights of multi-task learning are automatically adjusted to help the model better balance the learning process between the detection and correction network, enabling it to converge faster and achieve higher precision. Comprehensive evaluations demonstrate improved performance over existing baselines, particularly in addressing complex error patterns.

We report on the absorption, static, and transient luminescence spectra of Sm3+-doped glasses. The dependences between absorption and emission cross sections as well as between luminescence quantum efficiencies and Sm3+ doping concentration are examined. The large stimulated absorption cross section and emission cross section combined with the long fluorescent lifetime make phosphate glasses doped with Sm3+ promising material for visible fiber lasers. Moreover, ΔT(Tx − Tg) of these glasses is about 290 °C, which guarantees their thermal stability against crystallization during the fiber drawing process.