Analytics Seminar Series

One Text / Two Languages

February 15th, 2019

This workshop covered how linguists gather, process and analyze code-switched data, exploring the NPL pipeline for processing multilingual texts and discussing various approaches to language identification.

Hala Systems Inc. – Protect Everything That Matters

October 4th, 2018

Hala Systems develops advanced solutions for civilian and asset protection, accountability, and the prevention of violence before, during, and after conflict with the aim to reduce harm, increase security, and stabilize communities.

Working at the Intersection of Data Science and NLP

September 20th, 2018

A glimpse of work that occurs at the intersection of data science and natural language processing, including cross-cultural name matching, Arabic proximity search, Chinese IR for term highlighting, Korean word similarity, and emoji processing for sentiment analysis.

Scalable nd-arrays for Neuroimaging and Beyond

September 21st, 2018

This talk introduces Bolt, an open-source implementation of an ndarray built on PySpark. Bolt provides a familiar API enabling distributed computations across one or more array dimensions at a time…

The Silicon Petri Dish: Modeling, Simulation, and Data Science

December 14th, 2017

Using an initial set of assumptions about the state of the world derived from data analytics, a computer simulation model functioning as a “silicon petri dish” can be used to create synthetic data containing salient features of the real data set.

A Practitioner’s Look at Speech -to-Text

September 15th, 2017

Discussion of the basics of signal processing for speech recognition, acoustic and language models, and how they are jointly maximized to produce text.

Build Your Own Data Collection IoT Devices

October 16th, 2017

DIY technological devices, making, and hacking are becoming more and more accessible for anybody. Especially for creating your own data and doing your own analytics this trend offers exiting opportunities…

Big Data Analytics Using Public Clouds

May 4th, 2017

Big Data is no longer a buzz word. Public cloud is no longer the new kid in the block. The promise of elastic, reliable, inexpensive, managed services from public cloud providers has excited enterprises to store more data than ever before……