This inventor holds 1 USPTO granted patent. Top assignee: International Business Machines Corporation. Active years: 2024.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2024
Title: Innovations of Sukannya Purkayastha
Introduction
Sukannya Purkayastha is an accomplished inventor based in Dhubri, India. She has made significant contributions to the field of knowledge graph question answering through her innovative patent. Her work exemplifies the intersection of natural language processing and artificial intelligence.
Latest Patents
Sukannya holds a patent titled "Knowledge graph question answering with neural machine translation." This invention utilizes a modular two-stage neural architecture to translate natural language questions into logic forms, specifically SPARQL queries. The first stage employs a neural machine translation (NMT)-based sequence-to-sequence (Seq2Seq) model to create a SPARQL silhouette. In the second stage, a neural graph search module predicts the correct relations within the underlying knowledge graph. This innovative approach enhances the efficiency and accuracy of question answering systems.
Career Highlights
Sukannya is currently employed at International Business Machines Corporation, commonly known as IBM. Her role at IBM allows her to further develop her expertise in artificial intelligence and machine learning. She has demonstrated a strong commitment to advancing technology through her research and inventions.
Collaborations
Sukannya has collaborated with notable colleagues, including Saswati Dana and Dinesh Garg. These partnerships have contributed to her success and the development of her innovative projects.
Conclusion
Sukannya Purkayastha is a pioneering inventor whose work in knowledge graph question answering showcases her talent and dedication to advancing technology. Her contributions are paving the way for future innovations in artificial intelligence and natural language processing.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
