As you can see from the preceding results, our translation model is not behaving ideally. These results were obtained by running the optimization for more than 12 hours on a single NVIDIA 1080 Ti GPU. Also note that this is not even the full dataset, we only used 250,000 sentence pairs for training. However, if you type something into Google Translate, which uses the Google Neural Machine Translation (GNMT) system, the translation almost always looks very realistic with only minor mistakes. So it is important to know how we can improve the model so that it can produce better results. In this section, we will discuss several ways of improving NMTs such as teacher forcing, deep LSTMs, and attention mechanism.
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Natural Language Processing with TensorFlow
Thushan is a seasoned ML practitioner with 4+ years of experience in the industry. Currently he is a senior machine learning engineer at Canva; an Australian startup that founded the online visual design software, Canva, serving millions of customers. His efforts are particularly concentrated in the search and recommendations group working on both visual and textual content. Prior to Canva, Thushan was a senior data scientist at QBE Insurance; an Australian Insurance company. Thushan was developing ML solutions for use-cases related to insurance claims. He also led efforts in developing a Speech2Text pipeline there. He obtained his PhD specializing in machine learning from the University of Sydney in 2018.
Read more about Thushan Ganegedara
Unlock this book and the full library FREE for 7 days
Authors (2)
Thushan is a seasoned ML practitioner with 4+ years of experience in the industry. Currently he is a senior machine learning engineer at Canva; an Australian startup that founded the online visual design software, Canva, serving millions of customers. His efforts are particularly concentrated in the search and recommendations group working on both visual and textual content. Prior to Canva, Thushan was a senior data scientist at QBE Insurance; an Australian Insurance company. Thushan was developing ML solutions for use-cases related to insurance claims. He also led efforts in developing a Speech2Text pipeline there. He obtained his PhD specializing in machine learning from the University of Sydney in 2018.
Read more about Thushan Ganegedara