BERT-for-RRC-ABSA
BERT-for-RRC-ABSA copied to clipboard
howardhsu
code for our NAACL 2019 paper: "BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis"
Hello @howardhsu , This is a very nice repo.After reading the paper Understanding pretrained BERT4ABSA，Im interested in “probe”，could you please give some description about “L1-normed probe”？ in “ We train...
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...
1/ when running transformers/script/run_ft.sh, I wonder where I can find a example of json config file, the link in the description seem have been broken. 2/ In file transformers/plot/job.py I...
I need to have the polarity associated with particular words or phrases used to ensure that these are taken into account when associated with a particular aspect. Is there a...
Thanks for your work! I tried to post train the Bert base model using my own data. I encountered some problem when using fp16 (CUDA error: invalid configuration argument), so...
Thanks for your code！Could you please share the code which pretrains BERT with the unlabeled review data from Amason and Yelp？It would be better if we could see the code...
Hi, As you mentioned in this issue: #17 I have used the transformer-version code base to fine-tune the models. Here is the result that I got after running `bash script/run_ft.sh`,...
Could you please provide another method to download the yelp dataset, as the link provided in the paper [https://www.yelp.com/dataset/challenge]() has become invalid.😂 Thank you!
After downloading "post-trained Laptop weights" (fine-tuned model). How can I Evaluate using that weights for aspect Extraction? Thank you.
Hi can you give a sample implementation on how to run your model on specific user input from the pre-trained models? Can you guide with the demo pipeline to predict...
