awasthiabhijeet/PIE

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)

45
/ 100
Emerging

This project helps quickly correct grammatical errors in written text. You provide sentences that may contain mistakes, and it outputs revised sentences with improved grammar, spelling, and punctuation. It's designed for natural language processing researchers or developers who need a very fast and efficient way to process and correct large volumes of text.

231 stars. No commits in the last 6 months.

Use this if you need a high-speed solution for grammatical error correction that can process text significantly faster than traditional methods, while maintaining competitive accuracy.

Not ideal if you're looking for a simple, out-of-the-box spell checker or grammar tool for everyday use, as it requires technical setup and understanding of model inference.

natural-language-processing text-correction computational-linguistics machine-translation-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

231

Forks

39

Language

Macaulay2

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/awasthiabhijeet/PIE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.