DeepAI
Log In Sign Up

Neural Machine Translation of Logographic Languages Using Sub-character Level Information

09/07/2018
by   Longtu Zhang, et al.
0

Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/07/2019

SubCharacter Chinese-English Neural Machine Translation with Wubi encoding

Neural machine translation (NMT) is one of the best methods for understa...
03/01/2019

Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information

Unsupervised neural machine translation (UNMT) requires only monolingual...
11/12/2020

Inference-only sub-character decomposition improves translation of unseen logographic characters

Neural Machine Translation (NMT) on logographic source languages struggl...
06/13/2018

An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization

In this paper, we apply different NMT models to the problem of historica...
05/09/2018

wubi2en: Character-level Chinese-English Translation through ASCII Encoding

Character-level Neural Machine Translation (NMT) models have recently ac...
09/06/2018

Character-Aware Decoder for Neural Machine Translation

Standard neural machine translation (NMT) systems operate primarily on w...
05/27/2022

Patching Leaks in the Charformer for Efficient Character-Level Generation

Character-based representations have important advantages over subword-b...