Search

This study aims to explore the research methodology of applying the Transformer model algorithm to Chinese word sense disambiguation, seeking to resolve word sense ambiguity in the Chinese language. The study introduces deep learning and designs a Chinese word sense disambiguation model based on the fusion of the Transformer with the Bi-directional Long Short-Term Memory (BiLSTM) algorithm. By utilizing the self-attention mechanism of Transformer and the sequence modeling capability of BiLSTM, this model efficiently captures semantic information and context relationships in Chinese sentences, leading to accurate word sense disambiguation. The model's evaluation is conducted using the PKU Paraphrase Bank, a Chinese text paraphrase dataset. The results demonstrate that the model achieves a precision rate of 83.71% in Chinese word sense disambiguation, significantly outperforming the Long Short-Term Memory algorithm. Additionally, the root mean squared error of this algorithm is less than 17, with a loss function value remaining around 0.14. Thus, this study validates that the constructed Transformer-fused BiLSTM-based Chinese word sense disambiguation model algorithm exhibits both high accuracy and robustness in identifying word senses in the Chinese language. The findings of this study provide valuable insights for advancing the intelligent development of word senses in Chinese language applications., (© 2024. The Author(s).)

Background: Species of the genus Monascus are economically important and widely used in the production of food colorants and monacolin K. However, they have also been known to produce the mycotoxin citrinin. Currently, taxonomic knowledge of this species at the genome level is insufficient., Methods: This study presents genomic similarity analyses through the analysis of the average nucleic acid identity of the genomic sequence and the whole genome alignment. Subsequently, the study constructed a pangenome of Monascus by reannotating all the genomes and identifying a total of 9,539 orthologous gene families. Two phylogenetic trees were constructed based on 4,589 single copy orthologous protein sequences and all the 5,565 orthologous proteins, respectively. In addition, carbohydrate active enzymes, secretome, allergic proteins, as well as secondary metabolite gene clusters were compared among the included 15 Monascus strains., Results: The results clearly revealed a high homology between M. pilosus and M. ruber , and their distant relationship with M. purpureus . Accordingly, all the included 15 Monascus strains should be classified into two distinctly evolutionary clades, namely the M. purpureus clade and the M. pilosus - M. ruber clade. Moreover, gene ontology enrichment showed that the M. pilosus - M. ruber clade had more orthologous genes involved with environmental adaptation than the M. purpureus clade. Compared to Aspergillus oryzae , all the Monascus species had a substantial gene loss of carbohydrate active enzymes. Potential allergenic and fungal virulence factor proteins were also found in the secretome of Monascus . Furthermore, this study identified the pigment synthesis gene clusters present in all included genomes, but with multiple nonessential genes inserted in the gene cluster of M. pilosus and M. ruber compared to M. purpureus . The citrinin gene cluster was found to be intact and highly conserved only among M. purpureus genomes. The monacolin K gene cluster was found only in the genomes of M. pilosus and M. ruber , but the sequence was more conserved in M. ruber., Conclusion: This study provides a paradigm for phylogenetic analysis of the genus Monascus , and it is believed that this report will lead to a better understanding of these food microorganisms in terms of classification, metabolic differentiation, and safety., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Zhang, Cui, Chen, Li, Mao, Mao, Li, Guo, Wang, Liao and Liu.)