Under the Hood at Grammarly: Leveraging Transformer Language Models for Grammatical Error Correction | Grammarly Engineering Blog

This post is by Grammarly research scientists Dimitris Alikaniotis and Vipul Raheja.

This post is by Grammarly research scientists Dimitris Alikaniotis and Vipul Raheja. Over the past ten years, Grammarly has focused on building one of the world’s best writing assistants. One major aspect of this is grammatical error correction (GEC). It’s a core component of achieving our mission of improving lives by improving communication—from helping people craft a mistake-free social media post to supporting them in perfecting a cover letter for a dream job. To this end, we have made tremendous progress toward building an AI-powered system that achieves state-of-the-art performance in co

related reading

• Grammatical Error Correction: Tag, Not Rewrite | Grammarly Engineering Bloggrammarly.com
• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• Grammarly's NLP Team Builds the Future of Communication | Grammarly Engineering Bloggrammarly.com
• transformer_attention.pdfarxiv.org
• Text Simplification by Tagging | Grammarlygrammarly.com
• In-context Learning and Induction Headstransformer-circuits.pub
• A History of Large Language Modelsgregorygundersen.com
• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• Modular Pretraining Enables Access Controlalignment.anthropic.com
• The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• Large Language Models Reading List | Sebastian Raschka, PhDsebastianraschka.com
• Large Language Model: world models or surface statistics?thegradient.pub