ABSA-BERT-pair
ABSA-BERT-pair copied to clipboard
HSLCY
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (NAACL 2019)
When I make Step 3: train I got: 11/19/2020 18:11:54 - INFO - __main__ - device cpu n_gpu 0 distributed training False 0 guid= train-0 text_a= location - 2 ,...
Hi, thanks for making your codebase public. I walked through your preprocessing steps, and modeling part. And I could not find a place that you are weighting different classes or...
I run your code with CUDA_VISIBLE_DEVICES=0,1,2,3 python3 run_classifier_TABSA.py --task_name semeval_QA_B --data_dir data/semeval2014/bert-pair --vocab_file uncased_L-12_H-768_A-12/vocab.txt --bert_config_file uncased_L-12_H-768_A-12/bert_config.json --init_checkpoint uncased_L-12_H-768_A-12/pytorch_model.bin --eval_test --do_lower_case --max_seq_length 512 --train_batch_size 24 --learning_rate 2e-5 --num_train_epochs 12.0 --output_dir results_v2/semeval_result/QA_B...
Hello,I have read your paper,excellent work! But in the paper you may did not mention how the accuracy is calculated, now I know the sentiment ACC is ACC of the...
Hello. Is it possible to retrain this model? For example, at first train model on independent data and then train on text of certain type
Hi I am trying to use google/colab to train this Bert model. Would you be able to help me figure out how can I do so?! If not is there...
Hi, just to clarify, is the fine-tuned model saved to pytorch_model.bin automatically after training?
Do you have any information on the required hardware? I'm trying to run it on 1 GPU - 16GB - however CUDA goes out of memory.
Great article! Thank you for publishing the code! I am following your steps and on step 3 when I run the code for semeval_NLI_M I got this error:  ...
Hi, I am able to train the model by using the readme.md instructions but facing an issue during evaluation saying error "No file named test_ep_4.txt" I checked for that file...
