Contextual Text Denoising with Masked Language Model

Yifu Sun, Haoming Jiang


Abstract
Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual text denoising algorithm based on the ready-to-use masked language model. The proposed algorithm does not require retraining of the model and can be integrated into any NLP system without additional training on paired cleaning training data. We evaluate our method under synthetic noise and natural noise and show that the proposed algorithm can use context information to correct noise text and improve the performance of noisy inputs in several downstream tasks.
Anthology ID:
D19-5537
Volume:
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WNUT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
286–290
Language:
URL:
https://www.aclweb.org/anthology/D19-5537
DOI:
10.18653/v1/D19-5537
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-5537.pdf