by Lev Hladush
Grammarly is both the name of San-Francisco based company and their main product – a communication assistant that helps correct grammar and typos in word processing to any internet user.
What is especially exciting about Grammarly is that the work of their assistant relies heavily on Artificial Intelligence. Thus making it a particular object of interest for us, students of Management and Artificial Intelligence program. Grammarly uses AI to help millions of people worldwide make their communication clear, effective and error-free. Everyone knows that communication is key to both personal and professional success and the mission of the company to improve lives by improving communication. The big vision behind it is to help people articulate their thoughts in a way that’s clear and effective, in a way that makes them understood as intended.
Core to this mission has been the work in natural language processing (NLP). They rely on their team’s deep expertise in NLP, machine learning (ML) and AI. The way it works is something like this:
Broadly speaking, an artificial intelligence system mimics the way a human would perform a task. AI systems achieve this through different techniques. Machine learning, for example, is a particular methodology of AI that involves teaching an algorithm to perform tasks by showing it lots of examples rather than by providing a series of rigidly predefined steps.
Grammarly’s AI system combines machine learning with a variety of natural language processing approaches. Human language has many levels at which it can be analyzed and processed: from characters and individual words through grammatical structures and sentences, even paragraphs or full texts. Natural language processing is a branch of AI that involves teaching machines to understand and process human language (English, for instance) and perform useful tasks, such as machine translation, sentiment analysis, essay scoring, and, in our case, writing enhancement.
An important part of building an AI system is training it. AIs are kind of like children in that way. Kids learn how to behave by watching the people around them and by positive or negative reinforcement. As with kids, if you want your AI system to grow up to be helpful and functional, you need to be careful about what you expose it to and how you intervene when it gets things wrong.
The first step is choosing high-quality training data for your system to learn from. In Grammarly’s case, that data may take the form of a text corpus—a huge collection of sentences that human researchers have organized and labeled in a way that AI algorithms can understand. If you want your AI to learn the patterns of proper comma usage, for example, you need to show it sentences with incorrect commas, so it can learn what a comma mistake looks like. And you need to show it sentences with good comma usage, so it learns how to fix comma mistakes when it finds them.
AI systems also need feedback from humans. When lots of users hit “ignore” on a particular suggestion, for example, Grammarly’s computational linguists and researchers make adjustments to the algorithms behind that suggestion to make it more accurate and helpful.
Just like people, AI does sometimes make errors. It’s especially possible when an AI is facing a situation it doesn’t have much experience with. Grammarly is trained on naturally written text, so it’s good at spotting issues that occur naturally when people write. It’s less good at handling sentences where mistakes have been deliberately inserted because they often don’t resemble naturally occurring mistakes.
Sources: Grammarly.com
