Summary of Attention Is All You Need, by Ashish Vaswani et al.
Attention Is All You Need
by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
First submitted to arxiv on: 12 Jun 2017
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The Transformer model is a new architecture for sequence transduction that replaces complex recurrent or convolutional neural networks with attention mechanisms alone. This simple approach achieves state-of-the-art results in machine translation while being more efficient and parallelizable. The model’s performance is demonstrated on two tasks, English-to-German and English-to-French translation, where it sets a new single-model BLEU score record of 41.8. The Transformer also generalizes well to other tasks like constituency parsing, making it a promising tool for natural language processing. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The Transformer is a new way to translate languages using computers. It’s different from other methods that use big neural networks and attention mechanisms to find important words. This simple approach works really well and can even help with other tasks like breaking down sentences into their parts of speech. The best part? It takes much less time and computer power than the old ways, making it a super powerful tool for people who study language. |
Keywords
» Artificial intelligence » Attention » Bleu » Natural language processing » Parsing » Transformer » Translation
