Learning Word Vectors for 157 Languages

Re:Learning Word Vectors for 157 Languages by rspeer on Friday February 23, 2018 @05:32PM (#16450200)

I argue that you need both domain-general and domain-specific data. Most domains you could apply NLP to don't have billions of words to train on, especially if the language of the data isn't English.

Pre-trained data is valuable, and you really aren't going to re-learn it all from your data, so why throw it out?

[ Parent | on HN ]

Re:Learning Word Vectors for 157 Languages by laughingman2 on Friday February 23, 2018 @09:34PM (#16451304)

Yes, recent work on transfer learning https://arxiv.org/abs/1801.06146 " Fine-tuned Language Models for Text Classification" suggests that training a lstm on a large corpora for language modeling, then using it as sentence encoder after tuning it in specific dataset gives a considerable perfomance.

This is covered in fast.ai 's new course 1.

[ Parent | on HN ]