The Model Was Never the Bottleneck: What Shipping a Text Classifier Into a Government Office Taught
Items couldn't be added
The title couldn't be added to your basket.
Couldn't add title to Wish List
‘Remove from Wish List’ failed
Adding to library failed
‘Follow podcast’ failed
‘Unfollow podcast’ failed
-
Narrated by:
-
By:
This story was originally published on HackerNoon at: https://hackernoon.com/the-model-was-never-the-bottleneck-what-shipping-a-text-classifier-into-a-government-office-taught.
We shipped a Word2Vec+LSTM over a more accurate BERT, then load testing showed the model was 0.3% of the wall-clock time. The queue was five human reviewers.
Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #machine-learning, #nlp, #text-classification, #bert, #mlops, #human-in-the-loop-ai, #govtech, #model-selection, and more.
This story was written by: @vladimirbesk. Learn more about this writer by checking @vladimirbesk's about page, and for more stories, please visit hackernoon.com.
We built a classifier that sorts incoming citizen appeals into complaints, applications and proposals, and routes them to the right department. BERT was the most accurate model we tested. We shipped a smaller Word2Vec+LSTM instead. Then load testing showed that neither choice mattered much, because the queue was never in the GPU. It was in the five people doing review.