The Unreasonable Effectiveness of Deep Feature Extraction

Re:The Unreasonable Effectiveness of Deep Feature Extraction by stared on Thursday February 14, 2019 @03:04PM (#19165459)

Thanks for this reference, I will look it up. Though, from my experience people in NLP still (be default) train from scratch, with some exceptions for tasks on the same dataset:

- https://blog.openai.com/unsupervised-sentiment-neuron/

- http://ruder.io/nlp-imagenet/

[ Parent | on HN ]

Re:The Unreasonable Effectiveness of Deep Feature Extraction by samcodes on Friday February 15, 2019 @01:26AM (#19168898)

This is true, but rapidly changing. In addition to fine tuneable language models, you can do deep feature extraction with something like bert-as-service [0] ... You can even fine tune Bert on your days, then use the fine tuned model as a feature extractor.

[0] https://github.com/hanxiao/bert-as-service

[ Parent | on HN ]