Hello @howardhsu ,
This is a very nice repo. I am interested in running Bert_Review for E2E ABSA, which is possible according to the transformers.md file.
I can load the post-training weights using Transformers by running this code
`import torch
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("activebus/BERT_Review")
model = AutoModel.from_pretrained("activebus/BERT_Review")`
but how would I then use BERT_Review for E2E ABSA? For example a text.txt file with the example sentence: 'The food was good' to obtain 'food' as an aspect and 'POS' as a sentiment.
Hello @howardhsu ,
This is a very nice repo. I am interested in running Bert_Review for E2E ABSA, which is possible according to the transformers.md file.
I can load the post-training weights using Transformers by running this code
`import torch
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("activebus/BERT_Review")
model = AutoModel.from_pretrained("activebus/BERT_Review")`
but how would I then use BERT_Review for E2E ABSA? For example a text.txt file with the example sentence: 'The food was good' to obtain 'food' as an aspect and 'POS' as a sentiment.