Lune

ACL Findings2022

Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical Errors

Ryo Nagata, Manabu Kimura, Kazuaki Hanawa

Abstract

In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance equivalent to what a nonlanguage model-based method can achieve with the full training data; recall improves much faster with respect to training data size in the BERT-based method than in the non-language model method. This suggests that (i) the BERTbased method should have a good knowledge of the grammar required to recognize certain types of error and that (ii) it can transform the knowledge into error detection rules by fine-tuning with few training samples, which explains its high generalization ability in grammatical error detection. We further show with pseudo error data that it actually exhibits such nice properties in learning rules for recognizing various types of error. Finally, based on these findings, we discuss a cost-effective method for detecting grammatical errors with feedback comments explaining relevant grammatical rules to learners.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsKevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. ManningICLR 2020 · 541 citations
  2. Multi-Class Grammatical Error Detection for Correction: A Tale of Two SystemsZheng Yuan, Shiva Taslimipoor, Christopher Davis, Christopher BryantEMNLP 2021 · 28 citations
  3. Do Grammatical Error Correction Models Realize Grammatical Generalization?Masato Mita, Hitomi YanakaACL Findings 2021 · 8 citations
  4. How is BERT surprised? Layerwise detection of linguistic anomaliesBai Li, Zining Zhu, Guillaume Thomas, Yang Xu et al.ACL 2021

Related papers

  1. On the Robustness of Language Encoders against Grammatical ErrorsFan Yin, Quanyu Long, Tao Meng, Kai-Wei ChangACL 2020 · 32 citations
  2. Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error CorrectionGuangyue Peng, Wei Li, Wen Luo, Houfeng WangACL Findings 2025
  3. Effectiveness of Pre-training for Few-shot Intent ClassificationHaode Zhang, Yuwei Zhang, Li-Ming Zhan, Jiaxin Chen et al.EMNLP Findings 2021 · 40 citations
  4. Self-Correction Makes LLMs Better ParsersZiyan Zhang, Yang Hou, Chen Gong, Zhenghua LiEMNLP Findings 2025 · 5 citations
  5. Scaling Laws for BERT in Low-Resource SettingsGorka Urbizu, Iñaki San Vicente, Xabier Saralegi, Rodrigo Agerri et al.ACL Findings 2023 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines