Explosion Blog company blog
Embed, encode, attend, predict: the new deep learning formula for NLP models
Over the last six months, a powerful new neural network playbook has come together for Natural Language Processing. The new approach can be summarised as a simple four-step formula: embed, encode, attend, predict. This post explains the components of this new approach, and shows how they're put together in two recent…
- Points
- 140
- HN comments
- 16
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSoftware Engineering2016
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Nov 11, 2016 | Embed, encode, attend, predict: the new deep learning formula for NLP models by jast | 140 | 16 |
