#  How do a neural network model knows if a title is a letter title? 

 



 We are glad to share [our model](https://huggingface.co/cbdb/ClassicalChineseLetterClassification?text=%E4%B8%8A%E4%B8%9E%E7%9B%B8%E5%BA%B7%E6%80%9D%E5%85%AC%E6%9B%B8) to predict whether a phrase can be a letter title in Ming Dynasty. For example, this model can tell you 上丞相康思公書 can be a letter title. 劉先生墓誌銘 probabily can't be a letter title.

 In collaboration with [the Center for Chinese Studies 漢學研究中心](https://projects.iq.harvard.edu/cbdb/csa-ming-letters-project) and the efforts of our research assistant [Katherine Enright](https://github.com/KatherineMEnright), the China Biographical Database project created 438,000 records training data for letter titles. We fine-tuned a transformer model by these training data. The author of the codes are Queenie Luo queenieluo\[at\]g.harvard.edu.