search

chiayewken / Span-ASTE

Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".
MIT License
169 stars 45 forks source link

How to generate "predict_dev.jsonl" #36

Open Chen-PengF opened 1 year ago

Chen-PengF commented 1 year ago

when I run the file "main.py/main.sh", an error has occurred as follow:

Chen-PengF commented 1 year ago

File "Span-ASTE-main/aste/main.py", line 239, in eval with open(path) as f: FileNotFoundError: [Errno 2] No such file or directory: 'model_outputs/14lap_0/predict_dev.jsonl'

chiayewken commented 1 year ago

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

Chen-PengF commented 1 year ago

Hi, please use wrapper.py, I have updated the colab demo and demo.ipynb to the latest version Hi, but I have run the setup.py before wrapper.py, and there is still an error as follows:

File "/home/miniconda3/envs/span/lib/python3.7/site-packages/allennlp/common/params.py", line 352, in pop_choice raise ConfigurationError(message) allennlp.common.checks.ConfigurationError: span_model not in acceptable choices for dataset_reader.type: ['conll2003', 'interleaving', 'sequence_tagging', 'sharded', 'babi', 'text_classification_json']. You should either use the --include-package flag to make sure the correct module is loaded, or use a fully qualified class name in your config file like {"model": "my_module.models.MyModel"} to have it imported automatically.

Is this a version of allennlp problem?

chiayewken commented 1 year ago

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?

Also, are you using the demo notebook, if not, can you provide the exact command and you ran?

Chen-PengF commented 1 year ago

Thank you for your help. 1、This is my Python environment: Python 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] :: Anaconda, Inc. on Linux 2、I ran: bash setup.sh and show the picture for you [](https://pan.baidu.com/s/1pS-lIg43Uj3NH2EYwHHGaQ?pwd=hsfv 提取码：hsfv)

Chen-PengF commented 1 year ago

3、I run "python wrapper.py" for file wrapper.py

chiayewken commented 1 year ago

For training instructions, you can use the model as shown in the demo notebook or command-line style here:

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 data/triplet_data/14lap/dev.txt