Skip to content

Latest commit

 

History

History
16 lines (11 loc) · 694 Bytes

README.md

File metadata and controls

16 lines (11 loc) · 694 Bytes

NER-model

Using IDCNN and CRF to create a sequence labeling model.

This project uses IDCNN and CRF, combined with Word2Vec, to realize the IOBES named entity annotation of Chinese and English data

mainly reference

Composition of the project

  • main program - trains and tests the model, calls methods in other programs.
  • model program - set model parameters, build models, including CNN, CRF and word vector creation.
  • Other programs - data preprocessing functions, format conversion functions, data loading functions, etc.
  • Datasets - including Chinese and English datasets.

Enjoy！