Suraj Tripathi

I am a second year MLT (Master's in Language Technologies) student in the Language Technologies Institute, School of Computer Science at Carnegie Mellon University, advised by Prof. Teruko Mitamura.

I want to work towards enabling machines to understand and interact with their natural environment the same way humans do, by effectively interpreting language signals. My long term career goal is to test the limits of AI in the field of developing intelligent machines and one day have my research positively impact everyday life. I believe that there are still vast areas of research left unexplored before machines and humans are indistinguishable in their ability to understand and react to the natural environment. My research focuses on developing machine learning algorithms to bridge this gap both in language and multimodal settings.

My research with Prof. Teruko Mitamura is focused on event grounding across a set of extracted elements from multiple documents. These multiple documents are multimodal in nature and I work on finding the best match available between schema and graph G events given its temporal context, and various other attributes.

Before I joined CMU, I worked at Samsung Research Institute, Bangalore, India where I was a part of the Voice Intelligence Team. During my stay at Samsung, I got the opportunity to work on tasks from different modalities, for example, speech emotion recognition, natural language understanding, handling transformations in input images for computer vision tasks, etc. This helped me to understand the intricacies behind different modalities and has given me a strong research foundation to further build upon. Before that, I graduated with an M.Tech. in Computer Science from the Indian Institute of Technology, Delhi, and with a B.Tech. in Computer Science from Jamia Millia Islamia, Delhi, India. In my M.Tech. thesis, I worked on exploiting sparsity to attain faster run-time inference and compressed deep neural networks.