Saved in:
Bibliographic Details
Main Authors: Li, Xiangci, Liu, Hairong, Huang, Liang
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2011.06642
Tags: Add Tag
No Tags, Be the first to tag this record!
_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