Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)
A framework for assisting human while correcting the translation/OCR errors in documents, mostly dedicated to Indian Languages.
Automatic Post-Editing for Vietnamese
Materials for "DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages" at EMNLP'22 πΊοΈ
A robust and comprehensive translation system featuring a versatile backend pipeline that integrates MT with automatic error detection and an enriched UI that provides an intuitive platform for user corrections.
Code for "QE4PE: Word-level Quality Estimation for Human Post-Editing" βοΈ
JavaScript Notion-inspired text editor.
TranslationCorrect is a unified framework for MT annotation with predictive error detection and an intuitive post-editing interface, shown through a human study to reduce cognitive workload compared to traditional methods.
π Wrap non-error values into a proper Error subclass for better debugging and stack traces in JavaScript applications.
Analyse Post-Edit density data to create post-processing rules
π οΈ Build a pure Go GPT-style transformer from scratch to grasp the fundamentals of large language models without external libraries.
Add a description, image, and links to the post-editing topic page so that developers can more easily learn about it.
To associate your repository with the post-editing topic, visit your repo's landing page and select "manage topics."