Room Service is an Android app that helps students find unused classrooms on MIT campus. I worked with two other people to create this app. My main contribution was the backend functionality.
I scheduled a Python cron script on AWS Lambda to continuously pull updated information from the MIT Registrar's API. I also used Firebase for data storage.
Keywords: Java, Firebase, AWS Lambda
Our client Kevin is a visual designer on a user experience team. Reading dense work emails is a frustrating task for him because he has dyslexia. Kevin asked us to create a tool that would automatically restructure emails for him.
EasyMail has the following features:
* sentence separation onto individual lines,
* adjustable line and character spacing,
* question highlighting, and
* keyword highlighting.
Named Entity Recognition (NER) is a subtask of information extraction that involves identifying the names of persons, locations, and organizations in text. As a type of supervised learning, NER requires large sets of annotated data. Researchers have begun using crowdsourcing platforms like Amazon Mechanical Turk to collect annotations for large datasets.
I create a framework using Amazon Mechanical Turk to collect annotations across many domains (i.e. Wikipedia sports, New York Times education, etc.). In addition to preprocessing data, I designed a custom user interface that allows Turkers to annotate names of persons, locations, and organizations in selected text excerpts.