Sold by: MphasisÂ
Deployed on AWS
The solution uses a Double - Hard DeBias Algorithm to remove targeted biases from the vector space representation of a text corpus.
Overview
This solution uses an unsupervised learning method that solves problem of Bias in unstructured data (Text Corpus). It identifies and reduces the bias present in the word embeddings. The user can target a specific bias (Gender, Age, Race etc.) to be identified and mitigated, without loss in semantic meaning of words in the corpus. These trained and de-biased word vectors can then be utilized in language models powering applications like unbiased word prediction, unbiased word suggestion for replacement words in sentences, unbiased sentence generation, etc.
Highlights
- Bias: Detection & Mitigation algorithm is an unique implementation, able to handle unstructrued data like 'Text Corpus'. It performs all processes only based on user provided inputs (text corpus, bias specific seed words, bias direction defining pair of words, and category specific word list) in a single zip file. This algorithm also reduces Bias associated with frequency features in the Text corpus. The algorithm considers constraints such as minimum and maximum frequency of words in Text corpus, presence of symbols, Gender Direction etc.
- This solution is primarily optimized for gender De-Biasing case, but can be effectively and readily applied for any other case of Bias cases like Racism, Sexism, Ableism, etc. It can help organizations improve the bias neutrality in decision making through models using this algorithm's output DeBiased vectors. This solution also helps reduce the direct or indirect cost associated with lost revenues / customers, employees dissatisfaction, legal and compliance risk, damaged brand reputation etc.
- 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!
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.4xlarge Inference (Batch) Recommended | Model inference on the ml.m5.4xlarge instance type, batch mode | $0.00 |
ml.m5.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.4xlarge instance type, real-time mode | $0.00 |
ml.m5.4xlarge Training Recommended | Algorithm training on the ml.m5.4xlarge instance type | $10.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $0.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $0.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $0.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $0.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $0.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $0.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This is the first version
Additional details
Inputs
- Summary
- text corpus input contains text for which user wants to obtain debiased word vectors
- category word seeds contain unbiased keywords specific to the category
- definitional pairs contain keywords part of same group but opposite category
- bias specific full contains all keywords for categories considered for debiasing
- Limitations for input type
- Inferencing is done within training pipeline. Real time inference endpoint/batch transform job is not required.
- Input MIME type
- application/zip
https://github.com/Mphasis-ML-Marketplace/Bias-Detection-Mitigation-in-Text/tree/main/input
https://github.com/Mphasis-ML-Marketplace/Bias-Detection-Mitigation-in-Text/tree/main/input
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
text_corpus_input | * Input text file containing text corpus for which user wants to obtain debiased word vectors | Type: FreeText | Yes |
category_word_seeds | Category word seed text files containing unbiased keywords specific to the category | Type: Categorical
Allowed values: countryman,waiter,male | Yes |
definitional_pairs | Json file containing keywords part of same group but opposite category | Type: Categorical
Allowed values: ["woman", "man"], ["girl", "boy"] | Yes |
bias_specific_full | Json file containing all keywords for categories considered for debiasing | Type: Categorical
Allowed values: woman", "spokesman", "wife", "himself" | Yes |
Resources
Vendor resources
Support
Vendor support
For any product support you can reach out to us at:
AWS infrastructure support
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.
Similar products
Mphasis Responsible AI is a comprehensive framework that enables companies to develop and deploy robust, interpretable, explainable, bias-free, auditable and privacy preserving AI through a unique user experience and design thinking engagement. This makes the system trustworthy, thereby improving customer experience, reducing liability risk and ensuring regulatory compliance. We leverage our solution to engage with clients through assessments, workshops and implementations. We focus on specific parts of the most relevant use cases and help define the exact benefits to be derived from the initiative such as greater fairness, accountability, privacy, or algorithmic understanding and interpretability.
Weights & Biases provides AI developers with the tools needed to build models faster, fine-tune LLMs, and develop GenAI applications with confidence for enterprises of all sizes in any vertical.
Explainable AI solution that identifies algorithmic bias and thereby incorporate AI fairness
Model monitoring, data health, data drift detection, and AI observability.
Tumeryk AI Trust Score™ Guardrails provide real-time security and governance for GenAI agents and applications by enforcing jailbreak detection, bias monitoring, and content moderation. Integrated with tools like Wiz, Tumeryk also discovers Shadow AI and scores its risk, ensuring safe and compliant AI adoption.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.