Intro to Language Modeling (NLP video 8)

preview_player
Показать описание
We will revisit the problem of sentiment classification for movie reviews-- only this time we will use transfer learning and neural networks. We begin by using a language model pre-trained on Wikitext-103.

Рекомендации по теме
Комментарии
Автор

Hello, What do i do if i don't want to use the built in tokenization.
I actually have a small dataset and do not want to 'drop out' any words from it, i am fine with renaming of repeated words but i don't want the 'unknown' token, i want every word to be recognized.

mazharrazmian
Автор

This is just running cells on the Jupyter notebook. The explanations are not very intuitive

TheAnubhav