Chia Yew Ken

Hi, for inference of the relation extractor model, you can pass in the path of the data in a json file, based on the [code demo](https://colab.research.google.com/drive/18lrKD30kxEUolQ61o5nzUJM0rvWgpbFK?usp=sharing) and image below. The...

Hi, you can change the pretrained models to Chinese version in the [training stage](https://github.com/declare-lab/RelationPrompt#model-training--): eg "gpt2" -> "ckiplab/gpt2-base-chinese" eg "facebook/bart-base" -> "fnlp/bart-base-chinese"

Hi, the purpose of these commands is to use pre-downloaded [NLTK packages](https://www.nltk.org/nltk_data/) if they are available, because they may be slow to download in some countries. However, it is optional...

Hi, what is the command that you ran, is it following the model training steps here? https://github.com/chiayewken/Span-ASTE#model-training

Hi, after you have run the [installation steps](https://github.com/chiayewken/Span-ASTE#installation), you can run the training command below: ``` python aste/wrapper.py run_train_many \ --save_dir_template "outputs/14lap/seed_{}" \ --random_seeds [0,1,2,3,4] \ --path_train data/triplet_data/14lap/train.txt \ --path_dev...

Hi, thanks for pointing this out, I have updated the version and it should be fixed in the colab now https://colab.research.google.com/drive/1F9zW_nVkwfwIVXTOA_juFDrlPz5TLjpK?usp=sharing#scrollTo=izKXA4b6-oIv

Hi, it may be a difference in environment, is your notebook using GPU or CPU?

I'm not sure about the reason for errors with specific GPUs, but I have updated the pretrained weights and demo notebooks, please git pull to latest commit and try again,...

Hi, please use wrapper.py, I have updated the colab demo and demo.ipynb to the latest version

Hi, it may be an environment issue, can I check that you are using Python 3.7 and ran setup.sh based on the [installation instructions](https://github.com/chiayewken/Span-ASTE#installation)? Also, are you using the demo...