Research Assistant with Assistant Professor Michael Bernstein of CS Department
2013 - Present (about 6 years)
Project: Expert Crowdsourcing with Flash Teams
Accomplishment: Best Paper at UIST 2014. PDF: http://hci.stanford.edu/publications/2014/flashteams/flashteams-uist2014.pdf
- Built and optimized backends in Golang to serve code suggestions to a thin desktop client with low latency - Applied ranking and clustering techniques to a big dataset...more consisting Python code scraped from Github and StackOverflow
Accomplishment: Increased number of facts contributed to Knowledge Graph (KG) via GRASP by 30%, by improving the classifier component. The improvements...more ranged from large design changes to tuning classifier parameters to obscure bug fixes. GRASP is a pipeline that determines if extractions from the web are facts and adds only the high-precision ones (>99%) to KG.
Learning: Gained strong experience in machine learning and processing large amounts of data in a distributed fashion.
Wrote Hive/MapReduce scripts to retrieve specific data about users for targeted marketing purposes. For example, all users who have played at least one song of a particular language for the past 6 months.