Structural Form in Embeddings for Animals, Foods, and Cities
Algorithmically discovering structural form in data has been a topic of interest for several years.Continue readingStructural Form in Embeddings for Animals, Foods, and Cities
Author: dragnlabs
Haitian Translation Sensation Across the Nation
Automatic translation is a useful application of Artificial Intelligence. In recent years, as neural architectures have become more advanced, Neural Machine Translation (NMT) has been replacing traditional statistical translation methods as a standard practice. Continue readingHaitian Translation Sensation Across the Nation
Why are Words So Dang Hard?
I was invited to give a keynote address at the NeurIPS Workshop on Reinforcement and Language Learning in Text-Based Games.Continue readingWhy are Words So Dang Hard?
Analyzing Failure Modes
One advantage of many machine learning tasks is the ease with which we can measure model performance. Continue readingAnalyzing Failure Modes
Voice Control the World
We at DRAGN Labs are very interested in open-domain chatbots – bots that can converse intelligently on any topic, just like a human can.Continue readingVoice Control the World
Adventures in Data Collection
Using intent-mapping to facilitate more flexible speech interfaces. Continue readingAdventures in Data Collection