Gector – Grammatical Error Correction: Tag, Not Rewrite | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A continuously updated collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Gector -- Grammatical Error Correction: Tag, Not Rewrite

Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, Oleksandr Skurzhanskyi . Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications 2020 – 96 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Applications Model Architecture

In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an (F_{0.5}) of 65.3/66.5 on CoNLL-2014 (test) and (F_{0.5}) of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system. The code and trained models are publicly available.

Similar Work