Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?
Preprint
Abstract
This article offers an empirical study on the different ways of encoding Chinese, Japanese, Korean (CJK) and English languages for text classification. Different encoding levels are studied, including UTF-8 bytes, characters, words, romanized characters and romanized words. For all encoding levels, whenever applicable, we provide comparisons with linear models, fastText and convolutional networks. For convolutional networks, we compare between encoding mechanisms using character glyph images, one-hot (or one-of-n) encoding, and embedding. In total there are 473 models, using 14 large-scale text classification datasets in 4 languages including Chinese, English, Japanese and Korean. Some conclusions from these results include that byte-level one-hot encoding based on UTF-8 consistently produces competitive results for convolutional networks, that word-level n-grams linear models are competitive even without perfect word segmentation, and that fastText provides the best result using character-level n-gram encoding but can overfit when the features are overly rich.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Chinese–Spanish neural machine translation enhanced with character and word bitmap fontsMachine Translation, 2017
- Bag of Tricks for Efficient Text Classification2017
- Document classification through image-based character embedding and wildcard training2016
- Classes for fast maximum entropy training2002
- Some methods of speeding up the convergence of iteration methodsUSSR Computational Mathematics and Mathematical Physics, 1964