Sign in
Sign in
or
Create a new account
Categories
Your Saved List Become a Channel Partner Sell in AWS Marketplace Amazon Web Services Home Help

BERT Base Cased

Amazon Web Services | CPU

Reviews from AWS Marketplace

0 AWS reviews
  • 5 star
    0
  • 4 star
    0
  • 3 star
    0
  • 2 star
    0
  • 1 star
    0

External reviews

2 reviews
from G2

External reviews are not included in the AWS star rating for the product.

    Md. Rezowan T.

BERT Base Cased review

  • December 09, 2021
  • Review provided by G2

What do you like best about the product?
As it considers case of data, so, working with case sensitive things it gives better results.
What do you dislike about the product?
It required more training time than Bert uncased.
What problems is the product solving and how is that benefiting you?
We were building a spell checker.

    Anupam R.

Amazing and most advanced platform for doing quality analysis.

  • December 08, 2021
  • Review provided by G2

What do you like best about the product?
The best thing is to build a Pytorch dataset by tokenisation and padding. Very cleverly designed platform for preprocessing data.
What do you dislike about the product?
The one thing I did not like was for evaluation of the model. Sometimes it was showing error even if everything was perfect so that needs to be improved.
What problems is the product solving and how is that benefiting you?
I tried sentiment analysis using python and pytorch. The benefits are many such as easy to use interface, accessible libraries, and incredible performance.
Recommendations to others considering the product:
Always first prepare the data in the format that is commonly used by BERT. Then only start training the model otherwise it can become messy for you.

    Anupam R.

Amazing and most advanced platform for doing quality analysis.

  • December 08, 2021
  • Review provided by G2

What do you like best about the product?
The best thing is to build a Pytorch dataset by tokenisation and padding. Very cleverly designed platform for preprocessing data.
What do you dislike about the product?
The one thing I did not like was for evaluation of the model. Sometimes it was showing error even if everything was perfect so that needs to be improved.
What problems is the product solving and how is that benefiting you?
I tried sentiment analysis using python and pytorch. The benefits are many such as easy to use interface, accessible libraries, and incredible performance.
Recommendations to others considering the product:
Always first prepare the data in the format that is commonly used by BERT. Then only start training the model otherwise it can become messy for you.

showing 1 - 3