Benefits of Data Augmentation for NMT-based Text Normalization of User-Generated Content
Authors:
- Veronique HosteVHVeronique Hoste
Open Access
- 1 January 2019
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 275-285
Abstract
Claudia Matos Veliz, Orphee De Clercq, Veronique Hoste. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.Keywords
This publication has 12 references indexed in Scilit:
- Improving Deep Learning with Generic Data Augmentation2018
- Automatic detection of cyberbullying in social media textPLOS ONE, 2018
- Recent Trends in Deep Learning Based Natural Language Processing [Review Article]IEEE Computational Intelligence Magazine, 2018
- OpenNMT: Open-Source Toolkit for Neural Machine Translation2017
- Multimodular Text Normalization of Dutch User-Generated ContentACM Transactions on Intelligent Systems and Technology, 2016
- Transfer Learning for Low-Resource Neural Machine Translation2016
- Effective Approaches to Attention-based Neural Machine Translation2015
- Text Normalization in Social Media: Progress, Problems and Applications for a Pre-Processing System of Casual EnglishProcedia - Social and Behavioral Sciences, 2011
- Code eclecticism: Linguistic variation and code alternation in the chat language of Flemish teenagers1Journal of Sociolinguistics, 2010
- Normalization of non-standard wordsComputer Speech & Language, 2001