News for hackers. Stuff that matters.

A comment on What Kagglers Are Using for Text Classification. Parent comment

Re:What Kagglers Are Using for Text Classification by soraki_soladead on Thursday December 27, 2018 @12:23PM (#18770883)
For most businesses a GPU is not really expensive, particularly if the results are important to the business.

Chasing a single metric is certainly too narrow but getting the best results often does matter in a professional context too. While Kaggle can go overboard on massive ensembles using a state-of-the-art approach to the problem is often warranted outside of Kaggle.

[ Parent | on HN ]
Re:What Kagglers Are Using for Text Classification by scottlocklin on Thursday December 27, 2018 @10:42PM (#18774750)
Do you have an example backing up your assertions?

In my experience, the worst text classification is usually fine. Labels are usually too inaccurate and subjective for "accuracy" to matter much.

[ Parent | on HN ]
Re:What Kagglers Are Using for Text Classification by soraki_soladead on Friday December 28, 2018 @12:13AM (#18775013)
Electronic medical records. Anything in healthcare/medical, financial services, legal. There's a long way from the "worst text classification" to "sufficient text classification" in most real world use cases. With a reasonable budget you can relabel data and work around subjectivity.
[ Parent | on HN ]