After achieving state-of-the-art results, we’ve stepped up to higher-order aspects of communication. The vision for Grammarly began with spelling and grammar correction. Now we’re applying our mature infrastructure and domain knowledge to many exciting new challenges. And, we’ve cultivated an expert team where each member makes a direct impact. To make this possible, we’ve built a sophisticated portfolio of production models and a robust system for acquiring, curating, and annotating large amounts of diverse data. Other work that our ML/NLP team developed includes industry-leading grammatical error correction, clarity-improving sentence and paragraph rewrites, and identifying where readers are likely to focus in a text.
For example, just a handful of people built our tone detector feature, which helps users steer their messages to sound exactly how they intend. It’s an excellent time to join: We’ve spent over a decade investing in a mature ecosystem of linguistic and machine learning tools, but, because we’re a growing company, individuals still have a lot of ownership. If you’re interested in tackling these obstacles and improving human communication at a massive scale, we’re seeking talented, passionate folks to join Grammarly and boost our NLP and ML efforts.
The individuals on our NLP and ML team are essential here. We’re approaching these timely, complex problems head-on. Adding to these writing challenges is that now, more than ever, communication happens asynchronously and without the benefit of body language-making elements like sarcasm and tone all the more difficult to decipher.
This is why it’s very possible to write something that doesn’t quite land-that’s syntactically and grammatically correct, but nevertheless fails to communicate the intended message. Both writers and readers can bring different assumptions, contexts, and cultural backgrounds to a text, leaving room for misinterpretation. Language contains layers of meaning, intertwined with emotion. but because written communication is an astonishingly complex, multifaceted exchange. Ī case of curious contractions: “Book” was being modified by a singular (“every”) and a plural (“many”) determiner, triggering a bug (since fixed) in parsing the sentence that affected how our product treated the “n’t.” And not just because our models aren’t perfect. But, we feel like we’re only at the beginning. We rely on our team’s deep expertise in NLP, machine learning (ML), and linguistics to create a delightful product for Grammarly’s 30 million daily active users. Core to this mission has been our work in natural language processing (NLP). It went viral and is even used to teach English in Thailand.This article was co-written by Yury Markovsky, Engineering Manager Timo Mertens, Head of ML and NLP Products and Chad Mills, Manager, Applied Research and Engineering.Īt Grammarly, we are passionate about improving human communication. In 2016, writer, designer, and musician Reese Lansangan released the song “Grammar Nazi” about a woman upset with her love interest’s grammar. This means they may also be exhibiting some racism or classism. Grammar nazis also ignore the fact that Standard English is just one register of English, with other forms just as equally complex and valid, e.g., Black English or Appalachian English. This means they confuse a popular sense of so-called good/proper grammar (rules about what’s considered formal, good speaking, and writing) with linguistic grammar, which concerns the deeper structure of language.
Grammar nazis are not to be confused with editors and copyeditors, though some of them may occasionally fancy themselves as grammar nazis. The thing is, it’s just impossible to split infinitives in Latin, because they are always one word (e.g., amāre is “to love”). This “rule” came into force when English grammarians were just trying to make the language more like Latin, viewed as a more perfect tongue. Like splitting infinitives (e.g., to boldly go). The irony about grammar nazis is that many of the “rules” they like to impose on people are just flat-out bogus.
(You can totally do that, folks.) The phrase is recorded on a peeves-themed Usenet forum as early as 1990, five years before the TV sitcom Seinfeld featured its domineering Soup Nazi character. This use of nazi dates back to at least the 1950–60s, with self-styled surf nazis admitting their fanaticism for the waves. A grammar nazi is obsessively strict about formal rules of “grammar”-typically the little, often arbitrary stuff that a schoolmarm would correct a pupil for, like ending a sentence with a preposition. Nazis need no introduction: they were the German government and military who slaughtered over six millions Jews during World War II.Ī nazi, especially as written in lowercase, became a figure of speech for anyone seen as extremely authoritarian.