Technology Guru

Text data is everywhere Whether you are an established company or working to launch a new service, you can always leverage text data to validate, improve, and expand the functionalities of your product. The science of extracting meaning and learning from text data is an active topic of research called Natural Language Processing (NLP). NLP produces new and exciting results on a daily basis and is a very large field. However, having worked with hundreds of companies, the Insight team has seen a few key practical applications come up much more frequently than any other: Identifying different cohorts of users/customers (e.g. predicting churn, lifetime value, product preferences) Accurately detecting and extracting different categories of feedback (positive and negative reviews/opinions, mentions of particular attributes such as clothing size/fit…) Classifying text according to intent (e.g. request for basic help, urgent problem) While many NLP papers and tutorials exist onlin...

Writing today’s article was a fascinating experience for me and would also be for the readers of this blog. What’s so different? Two things: firstly the article is about something I always wanted to do since I was a 5-year old; secondly this topic / tools / algorithm is new to me as well. I am no way a master of image processing, but the utility of this field simply blew my mind. Imagine, if you can create an application of auto-tagging a photograph as that of Facebook, or create your own face recognition password to your laptop. In this article, I will pick up a very simple but interesting application of Image processing. We will use Python to do the image processing.  In the next few articles, I will take over more complex examples of Image Processing. Here is the problem I will be working on in this article: Problem Statement Guess what is this image? You are right, it’s a typical picture of an open sky. I took this picture last to last night in Bangalore f...

The two significant libraries used in NLP are NLTK and spaCy. There are substantial differences between them, which are as follows: NLTK provides a plethora of algorithms to choose from for a particular problem which is a boon for a researcher but a bane for a developer. Whereas, spaCy keeps the best algorithm for a problem in its toolkit and keep it updated as state of the art improves. NLTK supports various languages whereas spaCy have statistical models for 7 languages (English, German, Spanish, French, Portuguese, Italian, and Dutch). It also supports named entities for multi-language. NLTK is a string processing library. It takes strings as input and returns strings or lists of strings as output. Whereas, spaCy uses an object-oriented approach. When we parse a text, spaCy returns document object whose words and sentences are objects themselves. spaCy has support for word vectors whereas NLTK does not. As spaCy uses the latest and best algorithms, its performance is usually...

Google has removed the public version of their submit URL tool.  This tool allowed anyone to submit a URL to Google, as it wasn’t restricted to site owners only, Google Webmasters ✔ @googlewmc  ·  25 Jul Want to let us know about new or updated pages quickly? Use Search Console's Fetch & Submit for individual pages, or just have your CMS tell us directly with a sitemap file or feed. Find out more: https:// support.google.com/webmasters/ans wer/6065812  … Google Webmasters ✔ @googlewmc We've had to drop the public submission feature, but we continue to welcome your submissions using the usual tool in Search Console and through sitemaps directly. 3:55 PM - Jul 25, 2018 39 40 people are talking about this Twitter Ads info and privacy Why was this done?  While there were some site owners who used it to submit URLs who were unaware of Google Search Console, it is likely the majority ...

Today, the majority of the internet is supported by digital advertising. But bad ad experiences—the ones that blare music unexpectedly, or force you to wait 10 seconds before you get to the page—are hurting publishers who make the content, apps, and services we use every day. When people encounter annoying ads, and then decide to block all ads, it cuts off revenue for the sites you actually find useful. Many of these people don't intend to defund the sites they love when they install an ad blocker, but when they do, they block all ads on every site they visit.  Last year we  announced  Funding Choices to help publishers with good ad experiences recover lost revenue due to ad blocking. While Funding Choices is still in beta, millions of ad blocking users every month are now choosing to see ads on publisher websites, or “whitelisting” that site, after seeing a Funding Choices message. In fact, in the last month, over 4.5 million visitors who were asked to allow ads said...

Cancer is a complex and uncontrollable beast that mutates and changes the goalposts before you get into the politics and economics surrounding the issue. There isn’t just one cancer either – the homogenous term is misleading into thinking the problem is even solvable. Scientists and technologists alike are seeing hope though - not through increased funding but technological advancement in the form of Artificial Intelligence. Recently attending CogX  - one of the more robust and significant AI conferences in the UK - healthcare was very much on the menu. Medicine is already benefitting greatly from machine learning (a subset of AI) in areas from diagnosis to treatment, and we've barely scratched the surface. As more and more data becomes available – along with better computers and science – we start to see a shift happening. “Guilty Doctors” according to Professor Joanna Holbrook, Director Translational Biology, benevolent AI, are now up against a “humanly impossible amount ...