Our Favorite Posts Of Last Week (Jul 08, 2018)

HyperE

State-of-the-art word embeddings used in many natural language processing applications successfully encode the semantic relationships between words in the Euclidean space.
Link: https://hazyresearch.github.io/hyperE/
Word Count: 388

Use hreflang for language and regional URLs

Many websites serve users from around the world with content translated or targeted to users in a certain region. Google uses the rel="alternate" hreflang="x" attributes to serve the correct language or regional URL in Search results. Imagine you have an English language page hosted at http://www.
Link: https://support.google.com/webmasters/answer/189077
Word Count: 1064

Measuring the quality of popular keyword research tools

Ever wondered how the results of some popular keyword research tools stack up against the information Google Search Console provides? This article looks at comparing data from Google Search Console (GSC) search analytics against notable keyword research tools and what you can extract from Google.
Link: https://searchengineland.com/measuring-the-quality-of-popular-keyword-research-tools-299582
Word Count: 2441

Keras or PyTorch as your first deep learning framework

So, you want to learn deep learning? Whether you want to start applying it to your business, base your next side project on it, or simply gain marketable skills – picking the right deep learning framework to learn is the essential first step towards reaching your goal.
Link: https://deepsense.ai/keras-or-pytorch/
Word Count: 1745

Text Classification & Embeddings Visualization Using LSTMs, CNNs, and Pre-trained Word Vectors

Editor's note: This post summarizes the 3 currently-published posts in this series, while a fourth and final installment is soon on the way. In this tutorial, I classify Yelp round-10 review datasets.
Link: https://www.kdnuggets.com/2018/07/text-classification-lstm-cnn-pre-trained-word-vectors.html
Word Count: 508