The Amazing Ways Google And Grammarly Use Artificial Intelligence To Improve Your Writing

The Amazing Ways Google And Grammarly Use Artificial Intelligence To Improve Your Writing

While online editing tools such as Grammarly and grammar suggestions from Google Docs aren’t foolproof, the artificial intelligence and machine learning algorithms that power them are successfully improving the way many of us write. In the process, it saved millions of embarrassing errors caused by carelessness (there vs. They're) and, of course, caught mistakes that involved more challenging grammar rules. Whether we write an email, a text or something more formal, even professionals use these editing tools to detect errors before they mistakenly get broadcast. To really appreciate the technology that makes these editing tools possible, let's take a look at these services and the impressive ways they improve our writing.      

The Amazing Ways Google And Grammarly Use Artificial Intelligence To Improve Your Writing

Grammarly: The Leader of the Pack

Since its 2009 inception, cloud-based Grammarly has grown to more than 15 million daily active users and is often one of the top-ranked grammar checkers. Users can download the Grammarly Keyboard for their mobile devices, add an extension to Chrome, Firefox, Safari, Microsoft Edge, use the Grammarly Desktop App or download a plug-in for Microsoft Office so the algorithm can spell and grammar cheque on Word, social media and Outlook. Grammarly switched from a subscription-only model to a freemium model in 2015 to provide more access to users.

How does it work? Just like with other machine learning algorithms, Grammarly's artificial intelligence system was originally provided with a lot of high-quality training data to teach the algorithm by showing it examples of what proper grammar looks like. This text corpus—a huge compilation human researchers organised and labelled so the AI could understand it—showed, as an example, not only proper uses of punctuation, grammar and spelling, but incorrect applications so the machine could learn the difference. In addition, Grammarly’s system uses natural language processing to analyse every nuance of language down to the character level and all the way up to words and full paragraphs of text.

The feedback the system gets through humans when they ignore a proposed suggestion helps the system get smarter and provides the human linguists working with the input of the machine on how to make the system better. The more text it is exposed to, the better it can make appropriate suggestions. That's one of the reasons the company switched in 2010 to a consumer service from targeting enterprise customers so it would have access to a larger data set and a more significant opportunity.

In 2017, investors General Catalyst, IVP and Spark Capital committed $110 million to the already profitable company to help it further enhance its capabilities. Although the company has made great strides in improving grammar, grammatically correct writing doesn't necessarily mean it is compelling or concise. So, although the company has a history of adding new cheques such as to identify vagueness or plagiarism to improve your writing, expect this new infusion of funds to allow the company to add staff in an effort to continue improvements to its algorithm and the editing it can do. It has adequately tackled the basic mechanics of writing from spelling, grammar, and sentence structure as well as being able to help with clarity and readability of text. The next frontier is to provide context-specific suggestions.

Grammar Suggestions: Google Docs’ AI Grammar Checker

Grammarly may have recently introduced an extension of their own to work with Google Docs, but Google wants to get their own skin in the game with its grammar suggestions product. Google is using machine translation, the same tech they use to translate from one language to another (and one it has said approached human levels of accuracy), to power its editing tool. Instead of language to language, it translates poorly written text into grammatically correct text. If the system identifies a grammar issue, it will highlight it similar to how the spell cheque functionality works, so you have a chance to review possible grammar errors before hitting “send” or “publish.” Currently, details are limited about the new service, and the grammar cheque feature is only available via an early adopter programme.

These are undoubtedly intriguing developments, but we don't anticipate that they will take the place of a human writer anytime soon.

And according to the Grammarly Blog, “Our goal is to help you express yourself in the best way possible, whether you're applying for a job or texting a joke to your friends." Ultimately, the company desires to become "a true communication assistant that improves how people connect with and understand each other." It sounds like a brave mission any high school English teacher would support.    


Related Case Studies

 


 

Written by

Bernard Marr

Bernard Marr is a bestselling author, keynote speaker, and advisor to companies and governments. He has worked with and advised many of the world's best-known organisations. LinkedIn has recently ranked Bernard as one of the top 10 Business Influencers in the world (in fact, No 5 - just behind Bill Gates and Richard Branson). He writes on the topics of intelligent business performance for various publications including Forbes, HuffPost, and LinkedIn Pulse. His blogs and SlideShare presentation have millions of readers.

Some Of Our Customers

Connect with Bernard Marr