I am a Senior Research Programmer in Prof. Graham Neubig’s lab at the Language Technologies Institute of Carnegie Mellon University, working on research projects involving machine learning, multi-lingual natural language processing, machine translation etc.

Bio

I got my Masters degree in Computer Science at the Language Technologies Institute of Carnegie Mellon University, specializing in Speech Recognition and Natural Language Processing. After graduating, I continued working at CMU as a full-time research programmer and was involved in a number of research projects including IARPA BABEL (spoken term detection in low-resource languages), DARPA LORELEI (identifying topics, entities and events in low-resource languages, with an emphasis on humanitarian and disaster relief situations), DARPA AIDA (detecting alternative interpretations/narratives of real-world events in text and multimedia) and DARPA KAIROS (understand complex events described in text and multimedia by identifying, linking and temporally sequencing sub-events and their participants).

I also worked at a speech recognition startup (Voci Technologies, now part of Medallia Inc) for more than a year, where I was fortunate enough to be part of the team that built Voci’s core speech analytics software from the ground up. This product employed state-of-the-art speech recognition, transcription, and text analysis technologies (all built in-house) to help users visualize and gain insights from call center audio and other sources of real-world conversational speech.

Currently I am working with Prof. Graham Neubig on a project funded by Defence Science and Technology Agency (DSTA) Singapore. The project deals with social media summarization and narrative generation for humanitarian aid and disaster response situations, specifically in the low-resource languages setting.