Software
I’ve developed tools to support research on language and large-scale text data.
Blowtorch
macOS utility for connecting to NYU’s Torch cluster
Simplifies the process of working on the Torch supercomputing cluster by combining authentication, job submission, SSH, and IDE launch into a single interface.
lexichron
Tools for studying semantic change in large corpora
Pipelines for preparing and analyzing large text corpora (e.g., Google Ngrams and COHA). Supports data acquisition, filtering, restructuring, and training word embedding models..