用专家混合模型实现高效可解释的语法纠错，参数更少效果更好。
Efficient and Interpretable Grammatical Error Correction with Mixture of Experts
- 采用多专家架构，不同子网络专注纠正特定语法错误类型。
- 性能媲美T5-XL，有效参数减少三分之二。
- 纠错时同步识别错误类型，结果更可解释，适合需要透明性的场景。
错误类型信息被广泛用于提升语法纠错（GEC）模型性能，无论是生成修正、重排序还是组合多个GEC模型。利用在不同错误类型上具有互补优势的模型进行系统组合，能显著提高纠错质量。然而，系统组合需先运行基础模型再进行整合，计算开销巨大。因此，更高效的方式是设计一个单一模型，内含多个专精于不同错误类型的子网络。本文提出一种混合专家模型MoECE用于语法纠错。该模型在性能上达到T5-XL水平，但有效参数仅为三分之一。此外，模型在推理过程中可同时识别错误类型，提供可解释的修正结果。
原文摘要 · Abstract (English)
Error type information has been widely used to improve the performance of grammatical error correction (GEC) models, whether for generating corrections, re-ranking them, or combining GEC models. Combining GEC models that have complementary strengths in correcting different error types is very effective in producing better corrections. However, system combination incurs a high computational cost due to the need to run inference on the base systems before running the combination method itself. Therefore, it would be more efficient to have a single model with multiple sub-networks that specialize in correcting different error types. In this paper, we propose a mixture-of-experts model, MoECE, for grammatical error correction. Our model successfully achieves the performance of T5-XL with three times fewer effective parameters. Additionally, our model produces interpretable corrections by also identifying the error type during inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。