CNMBERT uses a multi-mask token strategy and Mixture of Experts layers to convert pinyin abbreviations to Chinese characters, outperforming GPT-4o and fine-tuned Qwen on the authors' test set.
Li et al., ‘Unified Named Entity Recognition as Word-Word Relation Classification’, arXiv [cs.CL]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters
CNMBERT uses a multi-mask token strategy and Mixture of Experts layers to convert pinyin abbreviations to Chinese characters, outperforming GPT-4o and fine-tuned Qwen on the authors' test set.