Developed a tool for document processing as part of the NLP core group using an
OCR engine, image processing, and NLP techniques to process unstructured data and
convert them to a structured format.
Built Computer Vision models to serve educational recommendations.
Manager: Mr. Anand Chandrasekaran, Founder and CTO
Part-Time Undergraduate Research & Teaching Assistant
Organization: Bright Academy (Previously Solarillion Foundation)
Location: Chennai, India
Duration: February 2020 - December 2022 (2 Yrs 11 Mos)
Collaborated on Terms of Service Classification, an NLP problem statement that uses a two-stage
knowledge distillation DL approach on low-resource devices with cutting-edge architectures like BERT
to find unfair Terms of Service terms.
Lead the NLP group that presented the "Sign Language Translation using Multi Context Transformer" paper
at the 20thMexican International Conference on Artificial Intelligence (MICAI), Mexico City, 2021.
To translate the input sign video, Multi Context Transformer architecture employs transformers and
runs on batched video inputs. Our model achieved comparable results with the state-of-the-art model while reducing
the parameters significantly to enable model deployment in more accessible devices.
Guided 5+ students in research, evaluated assignments and projects in Python and Machine Learning.
Oversaw the website development and managed the server for our research group.
Wrote bots for posting office hours and creating polls.
Advisor: Mr. Vineeth Vijayaraghavan, Director - Research and Outreach
Student Researcher
Organization: Sri Sivasubramaniya Nadar College Of Engineering
Location: Chennai, India
Duration: December 2020 - April 2022 (1 Yr 5 Mos)
Introduced a novel architecture for Fake News Detection based on Transformer architecture, which considers
the title and content of a news article to determine its integrity.
Our work was accepted for publication in the Science Citation Index Expanded journal: IOS Press - Journal of Intelligent & Fuzzy Systems, 2023.
Developed a robust and cost-effective automatic speech recognition model for Tamil language
leveraging Baidu's Deep Speech architecture. Our work was published in the Science Citation
Index Expanded journal: Intelligent Automation & Soft Computing, 2022.