TwASP models

Author: chenguimin

README.md

@@ -38,14 +38,16 @@ Note that Berkeley Neural Parser does not support `TensorFlow 2.0`.
 
 You can refer to their websites for more information.
 
-## Downloading BERT and ZEN
+## Downloading BERT, ZEN and TwASP
 
 In our paper, we use BERT ([paper](https://www.aclweb.org/anthology/N19-1423/)) and ZEN ([paper](https://arxiv.org/abs/1911.00720)) as the encoder.
 
 For BERT, please download pre-trained BERT-Base Chinese from [Google](https://github.com/google-research/bert) or from [HuggingFace](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz). If you download it from Google, you need to convert the model from TensorFlow version to PyTorch version.
 
 For ZEN, you can download the pre-trained model form [here](https://github.com/sinovation/ZEN).
 
+For TwASP, you can download the models we trained in our experiments from [here](https://github.com/SVAIGBA/TwASP/tree/master/models).
+
 ## Run on Sample Data
 
 Run `run_sample.sh` to train a model on the small sample data under the `sample_data` folder.

models/README.md

@@ -0,0 +1,16 @@
+## TwASP models
+
+| Section | BaiduNetDisk | Description |
+|-|-|-|
+|[TwASP.ZEN.CTB5]| [download](https://pan.baidu.com/s/1ebTaNXrw3P0E7wQaqZofkQ)(password: 2kul)| TwASP model trained on CTB5 dataset using ZEN as encoder |
+|[TwASP.ZEN.CTB6]| [download](https://pan.baidu.com/s/1rgLd2QT2txSTiYOT-fVRNg)(password: 1q59)| TwASP model trained on CTB6 dataset using ZEN as encoder |
+|[TwASP.ZEN.CTB7]| [download](https://pan.baidu.com/s/1d9SZD9soyv02J3BZr3NhBg)(password: krwr)| TwASP model trained on CTB7 dataset using ZEN as encoder |
+|[TwASP.ZEN.CTB9]| [download](https://pan.baidu.com/s/1Yw2-J_E7p3yaa5PleeGkpg)(password: 6jq2)| TwASP model trained on CTB9 dataset using ZEN as encoder |
+|[TwASP.ZEN.UD1]| [download](https://pan.baidu.com/s/1gvQx8g8SXJwTK0jqhrTAfg)(password: lrwu)| TwASP model trained on UD1 dataset using ZEN as encoder |
+|[TwASP.ZEN.UD2]| [download](https://pan.baidu.com/s/1roGP76Cggef8DvcheRGWjg)(password: mku5)| TwASP model trained on UD2 dataset using ZEN as encoder |
+|[TwASP.BERT.CTB5]| [download](https://pan.baidu.com/s/1g4rYCMulEW_nCtwQryU90Q)(password: mldm)| TwASP model trained on CTB5 dataset using BERT as encoder |
+|[TwASP.BERT.CTB6]| [download](https://pan.baidu.com/s/1XJd0Tr7KDnaXuDYIPYuoWg)(password: ro0m)| TwASP model trained on CTB6 dataset using BERT as encoder |
+|[TwASP.BERT.CTB7]| [download](https://pan.baidu.com/s/1FSZxe2cnkyRHEjLVK6Uejw)(password: wagb)| TwASP model trained on CTB7 dataset using BERT as encoder |
+|[TwASP.BERT.CTB9]| [download](https://pan.baidu.com/s/1s_8z20Ud6YohbG70wgheWA)(password: klw9)| TwASP model trained on CTB9 dataset using BERT as encoder |
+|[TwASP.BERT.UD1]| [download](https://pan.baidu.com/s/1wrN3unMWQGh1P3vxsqGvpw)(password: tnbh)| TwASP model trained on UD1 dataset using BERT as encoder |
+|[TwASP.BERT.UD2]| [download](https://pan.baidu.com/s/1gvPcyLCiAyhA_hkmijJmPw)(password: gs71)| TwASP model trained on UD2 dataset using BERT as encoder |