Work

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

Year: 2018

Type: conference-paper

Abstract: 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.

Source: Conference on Machine Translation (WMT)

DOI: 10.18653/v1/w18-6303

Authors: Longtu Zhang, Mamoru Komachi

Institution: Tokyo Metropolitan University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Japan Society for the Promotion of Science

Award: Grammatical Error Correction using Robust Word Representation Learning and Deep Neural Networks