Bengaluru, India

Mahima Shaha

This inventor holds 1 USPTO granted patent. Top assignee: Ge Precision Healthcare LLC. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Mahima Shaha. Retrieved from https://idiyas.com/inventor/mahima-shaha

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Mahima Shaha and Explainable Natural Language Processing

Introduction

Mahima Shaha is an inventor based in Bengaluru, India. Her patent work addresses explainability in natural language processing, with an application to clinical text.

Latest Patents

Shaha is associated with 1 patent, titled “Systems and Methods for Providing Explainability of Natural Language Processing.” The invention describes a system that analyzes a plain-text clinical sentence and uses a machine-learning model to classify the assertion status of a word of interest. It extracts word-wise attention scores from the model’s hidden attention layer and displays those scores alongside the classification label. A second machine-learning model uses the attention scores to determine a reliability score, which is also displayed.

Career Highlights

Shaha is associated with GE Precision Healthcare LLC. Her patent focuses on making machine-learning outputs for clinical language more interpretable by presenting both the classification and information about its reliability.

Collaborations

The provided information names Hrithik Auchar and Amar Kumar Gupta as Shaha’s coworkers. Their specific contributions to the patent are not stated.

Conclusion

Mahima Shaha’s patent describes an approach to explaining and assessing the reliability of natural-language processing results in clinical text.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…