esc and greco
These two tools are competitors, as both explore different system combination methods (frustratingly easy system combination vs. quality estimation) for grammatical error correction, each proposing a distinct approach to achieve improved performance in the same task.
About esc
nusnlp/esc
The official code of the "Frustratingly Easy System Combination for Grammatical Error Correction" paper
This project helps improve the accuracy of Grammatical Error Correction (GEC) systems. If you have multiple GEC tools that each produce a corrected version of text, this combines their outputs to create a single, more accurate corrected text. Researchers and developers working on GEC models can use this to enhance their system's performance.
About greco
nusnlp/greco
The official code for the "System Combination via Quality Estimation for Grammatical Error Correction" paper, published in EMNLP 2023.
This tool helps language researchers and developers working on writing assistance to combine multiple grammatical error correction (GEC) models for better results. It takes original sentences and various corrected versions from different GEC models. The output is a single, improved corrected sentence for each original sentence, along with scores indicating correction quality.
Scores updated daily from GitHub, PyPI, and npm data. How scores work