Context-aware Stand-alone Neural Spelling Correction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2020
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909611393548288 |
|---|---|
| author | Li, Xiangci Liu, Hairong Huang, Liang |
| author_facet | Li, Xiangci Liu, Hairong Huang, Liang |
| contents | Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. Inspired by this, we address the stand-alone spelling correction problem, which only corrects the spelling of each token without additional token insertion or deletion, by utilizing both spelling information and global context representations. We present a simple yet powerful solution that jointly detects and corrects misspellings as a sequence labeling task by fine-turning a pre-trained language model. Our solution outperforms the previous state-of-the-art result by 12.8% absolute F0.5 score. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2011_06642 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Context-aware Stand-alone Neural Spelling Correction Li, Xiangci Liu, Hairong Huang, Liang Computation and Language Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. Inspired by this, we address the stand-alone spelling correction problem, which only corrects the spelling of each token without additional token insertion or deletion, by utilizing both spelling information and global context representations. We present a simple yet powerful solution that jointly detects and corrects misspellings as a sequence labeling task by fine-turning a pre-trained language model. Our solution outperforms the previous state-of-the-art result by 12.8% absolute F0.5 score. |
| title | Context-aware Stand-alone Neural Spelling Correction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2011.06642 |