NLP/ML
Advancing AI-Powered Intelligent Writing Assistance across Multiple LanguagesThe Strategic Research team at Grammarly is constantly exploring how LLMs can contribute to our mission of improving lives by...December 6, 2024
Unlocking Personalization With an On-Device Model for the Grammarly KeyboardHasn’t everyone wished, at some point or another, that their phone keyboard understood them a little better? We’ve all...October 9, 2024
Detecting Delicate Text: Going Beyond ToxicityProtecting users from harmful communications is something we care about deeply at Grammarly. For that reason, our research has...January 25, 2024
CoEdIT: State-of-the-Art Text Editing With Fewer ParametersThis article was co-written by applied research scientists Vipul Raheja and Dhruv Kumar. Introduction At Grammarly, we’re...December 7, 2023
Improving the Performance of NLP Systems on the Gender-Neutral “They”At the core of Grammarly is our commitment to building safe, trustworthy AI systems that help people communicate. To do this, we...October 31, 2023
How We Created Personalized Snippet Suggestions Without Storing User TextWith Grammarly Business, we help our users communicate better and stay productive. The snippets feature is designed for exactly...January 18, 2023
Learning Where to Edit: Introducing DELIteraTeR, a Delineate-and-Edit Approach to Iterative Text RevisionThis article was co-written by applied research scientists Vipul Raheja and Dhruv Kumar. When you read a piece of high-quality...December 15, 2022
UA-GEC 2.0: Announcing an Expanded Grammatical Error Correction Dataset for the Ukrainian LanguageWe’re happy to announce UA-GEC 2.0, the second version of Grammarly’s publicly available grammatical error correction (GEC)...November 8, 2022
Annotation Best Practices for Building High-Quality DatasetsThis article was co-written by Analytical Linguists Lena Nahorna and Lily Ng. When working with language data to develop machine...October 24, 2022
Experimenting with GECToR: Research into Ensembling and Knowledge Distillation for Large Sequence TaggersGrammatical error correction (GEC) is an important problem in natural language processing (NLP) research. It refers to how we...June 29, 2022
Shape the way millions of people communicate every day!