ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark
This work assesses ChatGPT's potential for grammatical error correction, highlighting limitations in automatic evaluation for AI language models, which is incremental as it applies an existing model to a new task.
The study evaluated ChatGPT on the Grammatical Error Correction task using the CoNLL2014 benchmark, finding it underperformed compared to commercial tools like Grammarly and state-of-the-art models in automatic metrics, particularly on long sentences, but human evaluation showed it produced fewer under-corrections and mis-corrections, though more over-corrections.
ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions. In this report, we aim to evaluate ChatGPT on the Grammatical Error Correction(GEC) task, and compare it with commercial GEC product (e.g., Grammarly) and state-of-the-art models (e.g., GECToR). By testing on the CoNLL2014 benchmark dataset, we find that ChatGPT performs not as well as those baselines in terms of the automatic evaluation metrics (e.g., $F_{0.5}$ score), particularly on long sentences. We inspect the outputs and find that ChatGPT goes beyond one-by-one corrections. Specifically, it prefers to change the surface expression of certain phrases or sentence structure while maintaining grammatical correctness. Human evaluation quantitatively confirms this and suggests that ChatGPT produces less under-correction or mis-correction issues but more over-corrections. These results demonstrate that ChatGPT is severely under-estimated by the automatic evaluation metrics and could be a promising tool for GEC.