Amazon Sagemaker
Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.
Automated sentiment label correction
By:
Latest Version:
1.2
This solution helps in automatic labelling and correction of label errors in a sentiment analysis dataset
Product Overview
This solution takes in the unlabeled dataset and obtains weak labels using BERT based pre-trained model for sentiment classification. It also identifies the errors present in the generated weak labels using confidence learning methods using the predicted probability scores.The output contains orginal dataset split into two subsets, 1) Subset 1 of Clean labels (positive, negative or neutral) that could be directly used for downstream applications 2) Subset 2 of data that will have label errors that can be further subjected to manual validation
Key Data
Version
By
Type
Model Package
Highlights
This solution leverages a data-centric approach to find the label errors in a sentiment classification dataset which helps to improves the quality of data and is extremely pertinent to any downstream supervised model-centric workflow.
This solution can be used to obtain automated sentiment class labels for 3 sentiment classes: positive, negative and neutral, in cases where you have only unlabelled dataset to start with. It can be applied to datasets such are product reviews, tweets, social- media posts and financial news to capture the sentiment of the provided text.
PACE - ML is Mphasis Framework and Methodology for end-to-end machine learning development and deployment. PACE-ML enables organizations to improve the quality & reliability of the machine learning solutions in production and helps automate, scale, and monitor them. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Not quite sure what you’re looking for? AWS Marketplace can help you find the right solution for your use case. Contact us
Pricing Information
Use this tool to estimate the software and infrastructure costs based your configuration choices. Your usage and costs might be different from this estimate. They will be reflected on your monthly AWS billing reports.
Contact us to request contract pricing for this product.
Estimating your costs
Choose your region and launch option to see the pricing details. Then, modify the estimated price by choosing different instance types.
Version
Region
Software Pricing
Model Realtime Inference$8.00/hr
running on ml.m5.large
Model Batch Transform$16.00/hr
running on ml.m5.large
Infrastructure PricingWith Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
With Amazon SageMaker, you pay only for what you use. Training and inference is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and inference instances.
Learn more about SageMaker pricing
SageMaker Realtime Inference$0.115/host/hr
running on ml.m5.large
SageMaker Batch Transform$0.115/host/hr
running on ml.m5.large
Model Realtime Inference
For model deployment as Real-time endpoint in Amazon SageMaker, the software is priced based on hourly pricing that can vary by instance type. Additional infrastructure cost, taxes or fees may apply.InstanceType | Realtime Inference/hr | |
|---|---|---|
ml.m4.4xlarge | $8.00 | |
ml.m5.4xlarge | $8.00 | |
ml.m4.16xlarge | $8.00 | |
ml.m5.2xlarge | $8.00 | |
ml.p3.16xlarge | $8.00 | |
ml.m4.2xlarge | $8.00 | |
ml.c5.2xlarge | $8.00 | |
ml.p3.2xlarge | $8.00 | |
ml.c4.2xlarge | $8.00 | |
ml.m4.10xlarge | $8.00 | |
ml.c4.xlarge | $8.00 | |
ml.m5.24xlarge | $8.00 | |
ml.c5.xlarge | $8.00 | |
ml.p2.xlarge | $8.00 | |
ml.m5.12xlarge | $8.00 | |
ml.p2.16xlarge | $8.00 | |
ml.c4.4xlarge | $8.00 | |
ml.m5.xlarge | $8.00 | |
ml.c5.9xlarge | $8.00 | |
ml.m4.xlarge | $8.00 | |
ml.c5.4xlarge | $8.00 | |
ml.p3.8xlarge | $8.00 | |
ml.m5.large Vendor Recommended | $8.00 | |
ml.c4.8xlarge | $8.00 | |
ml.p2.8xlarge | $8.00 | |
ml.c5.18xlarge | $8.00 |
Usage Information
Model input and output details
Input
Summary
The user needs one csv file containing a text column that has the sentiment analysis data
Input MIME type
text/csvSample input data
Output
Summary
The output file (zip file) contains the following files:
- 'label_error.csv': the rows of label errors that can be manually looked into as csv output
- 'clean_label.csv': clean labels which are the more confident predictions which do not consist of such label errors as csv output.
- 'label_error.json': the label errors found in json format
- 'weak_label.csv': weak labels with lesser confidence on labels using pretrained model as csv file
Output MIME type
application/zipSample output data
Sample notebook
Additional Resources
End User License Agreement
By subscribing to this product you agree to terms and conditions outlined in the product End user License Agreement (EULA)
Support Information
AWS Infrastructure
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Learn MoreRefund Policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Customer Reviews
There are currently no reviews for this product.
View allWrite a review
Share your thoughts about this product.
Write a customer review