How do you decide which out of the box NLP model to use for named entity recognition ?
Ever wonder what problem you are solving with a tremendous model and 1000 GPUs ?
Labeling Data makes or breaks an NLP project. We describe the seven stages of a successful labeling project
A technique to get interactive high dimensional charts in React
Machine in the loop techniques reduce the cost of annotation but introduce bias. We discuss how to manage that tradeoff.
Character level models for NLP facilitate large vocabularies and remove computational bottlenecks during model training. This post reviews those traits and discusses the drawbacks of character level models for NLP.
We explain the motivation behind Tensorflow's Exstimator API, the problems it solves and how to use it
Three tips and tricks to get more labeled data with less work
How a company used NLP to annotate chest X-rays and what we can learn
Active Learning promises to reduce the labeling cost for building a model. We look into how that works out and ask if active learning delivers on what we really need
Postmortem analysis of a production bug where a customer as shown the wrong version of our frontend