Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation

By Zhaohong Wan, Xiaojun Wan, Wenguang Wang. 2020

42 citations recorded by the source corpus.

The incorporation of data augmentation method in grammatical error correction task has attracted much attention. However, existing data augmentation methods mainly apply noise to tokens, which leads to the lack of diversity of generated errors. In view of this, we propose a new data augmentation method that can apply noise to the latent representation of a sentence.By editing the latent representations of grammatical sentences, we can generate synthetic samples with various error types. Combining with some pre-defined rules, our method can greatly improve the performance and robustness of existing grammatical error correction models. We evaluate our method on public benchmarks of GEC task and it achieves the state-of-the-art performance on CoNLL-2014 and FCE benchmarks.

Subfields: Artificial Intelligence, Natural Language Processing, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Furu Wei
2. Kevin Gimpel
3. Tao Ge
4. Karen Livescu
5. John Wieting
6. Xin Sun
7. Houfeng Wang
8. Mohit Bansal

In Natural Language Processing

1. Kevin Gimpel
2. Furu Wei
3. Karen Livescu
4. Tao Ge
5. Xin Sun
6. John Wieting
7. Houfeng Wang
8. Freda Shi

In Natural Language Generation

1. Xin Sun
2. Kevin Gimpel
3. Houfeng Wang
4. Karen Livescu
5. Furu Wei
6. Tao Ge
7. Freda Shi

Citations in the corpus

• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding (2021, background): “2019; Lichtarge et al., 2019; Zhou et al., 2020; Wan et al., 2020), most methods that improve performance (Ge et al., 2018b; Kaneko et al., 2020) introduce additional computational cost and thus slow down inference despite the performance improvement.”
• Substructure Substitution: Structured Data Augmentation for NLP (2021, methodology): “…generating new examples by training a conditional text generation model (Bergmanis et al., 2017; Liu et al., 2020a; Ding et al., 2020; Liu et al., 2020b, inter alia ), or applying post-processing on the examples generated by pretrained models (Yang et al., 2020; Wan et al., 2020; Yoo et al., 2020).”