NLP/ML - Page 2
How Grammarly’s NLP Team Is Building the Future of CommunicationThis article was co-written by Yury Markovsky, Engineering Manager; Timo Mertens, Head of ML and NLP Products; and Chad Mills,...February 25, 2021
Adversarial Grammatical Error CorrectionIn developing the world’s leading writing assistant, Grammarly helps people communicate wherever they write—whether in an...January 26, 2021
Doing Data Right: Building a Successful Dataset From the Ground UpIn recent years, rapid developments in AI have made it possible for anyone with a basic background in computer science to...December 2, 2020
Grammatical Error Correction: Tag, Not RewriteGrammarly’s writing assistant helps with a wide variety of language and communication issues. One important aspect of this is...July 14, 2020
Earnings for earrings: mitigating gender bias in autocorrectIf you’ve ever used the spell-checker or autocorrect function in a popular product, you may have been a victim of gender bias in...April 7, 2020
Plainly speaking: a linguistic approach to simplifying complex wordsWould you like to peruse a report on how to elucidate overwrought verbiage? Or maybe you’d like to read an article on how to...February 5, 2020
Under the Hood at Grammarly: Leveraging Transformer Language Models for Grammatical Error CorrectionThis post is by Grammarly research scientists Dimitris Alikaniotis and Vipul Raheja. Over the past ten years, Grammarly has...August 7, 2019
Under the Hood at Grammarly: Understanding Conversational Sequences with AIThis post was written with Joel Tetreault, the director of research at Grammarly. A majority of our communication now happens...May 30, 2019- Paving the Way for Human-Level Sentence CorrectionsThe original article on which this post is based was co-written with Joel Tetreault and Keisuke Sakaguchi. This post was written...March 31, 2017
- The Dirty Little Secret of Constituency Parser EvaluationThis article was co-written with Grammarly engineer Vsevolod Dyomkin. The task of comparing constituency parsers is not a trivial...November 3, 2014
Shape the way millions of people communicate every day!