Hacker News new | past | comments | ask | show | jobs | submit login

In NLP, tokenization is one of the first steps in the pipeline to break down text into individual words. I don't know about others but for the project I'm doing, the tokenization speed doesn't matter much in the big picture because the following steps take much longer.



It matters for anything that should be more or less realtime, so where fast feedback is needed.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: