Our Favorite Posts Of Last Week (Dec 09, 2018)

Google search now supports live streams with Indexing API, structured data

Google announced it now supports better discovery of livestreams in Google Search and Google Assistant. These live streams can show up in the search results in a carousel and have a live label like the older live blog posts feature Google had back in 2015. Livestream structured data.
Link: https://searchengineland.com/google-search-now-supports-live-streams-with-indexing-api-structured-data-309117
Word Count: 284

HMTL - Multi-task Learning for solving Natural Language Processing (NLP) Tasks

The field of Natural Language Processing includes dozens of tasks, among them machine translation, named-entity recognition, and entity detection. While the different Natural Language Processing (NLP) tasks are often trained and evaluated separately, there exists a potential advantage in combining them into one model, i.e.
Link: https://towardsdatascience.com/hmtl-multi-task-learning-for-solving-Natural Language Processing (NLP)-tasks-cfae39b3d6e1
Word Count: 1495

Using Python in Power BI

Microsoft announced Python integration in Power BI in their August feature summary. Just as with the R support you can now use Python for importing data, data transformation and data visualization.
Link: https://towardsdatascience.com/using-python-in-power-bi-ee95a6b71443
Word Count: 2392

Measuring the "Filter Bubble": How Google is influencing what you click

Over the years, there has been considerable discussion of Google's "filter bubble" problem. Put simply, it's the manipulation of your search results based on your personal data.
Link: https://spreadprivacy.com/google-filter-bubble-study/
Word Count: 1966

Rich Results expands for Question & Answer pages

In order to help users better identify which search results may give the best information about their question, we have developed a new rich result type for question and answer sites. Search results for eligible Q&A pages display a preview of the top answers.
Link: https://webmasters.googleblog.com/2018/12/rich-results-expands-for-question.html
Word Count: 166

Deep Transfer Learning for Natural Language Processing — Text Classification with Universal Embeddings

Transfer learning is an exciting concept where we try to leverage prior knowledge from one domain and task into a different domain and task. The inspiration comes from us humans itself, where in, we have an inherent ability to not learn everything from scratch.
Link: https://towardsdatascience.com/deep-transfer-learning-for-natural-language-processing-text-classification-with-universal-1a2c69e5baa9
Word Count: 3782