谷歌神经机器翻译的汉译英错误例析及其翻译策略与建议研究

A Study on the Chinese- English Translation Errors Exemplified by Google Neural Machine Translation and the Translation Strategies amp; Suggestions

By Su Yue

In partial fulfillment of the requirement

For the B.A. degree

Department of English

College of Liberal Arts

Nanjing University of Information Science amp; Technology

May, 2018

Acknowledgements

The thesis is of great significance in my college life. From the topic selection to the fulfillment of this paper, every step is a new attempt and also a challenge for me. Hence, I would like to express my sincere appreciation to all who helped and encouraged me.

First of all, my heartfelt gratitude goes to my supervisor Professor Zhang Jun. Under his guidance and encouragement, I got the confidence to finish my paper. I am often deeply impressed by his modesty, reliability and diligence. During the process of writing of this thesis, he provided me with valuable instruction and insightful supervision, without which the completion of my thesis could not have been finished.

Besides, words of deep gratitude must be given to my teammates. They spare no efforts to help me. I am really grateful to them for their selfless contribution and silent support.

Last but not least, my gratitude goes to all of my family members and friends who have been a constant source of spiritual strength. They always give me energy to complete this thesis.

CONTENTS

Abstract: 1

Chapter One: Introduction 2

1.1 An overview of machine translation 2

1.2 Google Neural Machine translation 3

Chapter Two: Chinese- English Translation Errors Exemplified by Google Neural Machine

Tanslation and Their Causes 4

2.1Chinese-English Translation Errors Exemplified by Google Neural Machin

Translation 4

2.2Causes of errors 7

2.2.1 Syntactical differences between Chinese and English 7

2.2.2 Cultural barriers between Chinese and English 8

Chapter Three: Translation Strategies and Suggestions 9

3.1 Conversion of word classes 9

3.2 Adding subjects 10

3.3 Attaching great importance to free translation and literal translation 12

3.4 Suggestions 13

Chapter Four: Conclusion 14

References 15

A Study on the Chinese- English Translation Errors Exemplified by Google Neural Machine Translation and the Translation Strategies amp; Suggestions

Su Yue

Department of English

College of Liberal Arts

Nanjing University of Information Science and Technology, Nanjing 210044

Abstract: With the development and progress of science and technology, the accuracy of machine translation has been greatly improved compared with the past. Google in 2016 announced that the Google Neural Machine translation (GNMT) can effectively reduce the quality gap between the machine translation and the artificial translation, but there are still some deficiencies to be improved.

This paper consists of four chapters: Chapter One is the introduction. A brief introduction of machine translation and Google neural machine translation system will be made in this chapter. Chapter Two presents three kinds of machine translation errors and probes into the causes of flaws. Chapter Three puts forward the translation strategies and makes suggestions for GNMT to improve the accuracy of translation. Chapter Four is the conclusion. A brief summary of the whole paper,the limitations of this paper and suggestions for further study will be presented.

Key words: GNMT; Chinese-English translation errors; Translation strategies and suggestions

摘要：随着科技的发展进步，机器翻译的译文准确度相较过去有了大幅的提高。谷歌公司在2016年宣称谷歌神经机器翻译系统（GNMT）能够有效缩小机器译文与人工译文的质量差距，但其仍然存在着一些不足有待改进。

本文共四章构成，第一章是引言，简单介绍了机器翻译和谷歌神经机器翻译系统；第二章分析总结GNMT中的汉译英实例容易出现的三类错误及其原因；第三章将针对谷歌神经机器翻译引起译文错误的原因提出一系列翻译策略和建议，从而提高译文准确度；第四章是结论，对全文进行总结概括，提出本文的不足以及为进一步研究提供建议。

关键词：谷歌神经机器翻译；汉译英翻译错误；翻译策略与建议

Chapter One: Introduction

1.1 An overview of machine translation

“Although machine translation is very popular at present, the readability of the target language texts is far from satisfaction. A large quantity of researches have been done aiming to optimize the quality of machine translation.” (Hu, 2012: II) Nevertheless, there is still a large amount of work to be done to comprehensively develop machine translation engines.

In the age of big data, the rapid development of language technology has promoted the professionalization of translation. The industrialized and collaborative translation service has become progressively prominent. Meanwhile, the role of machine translation and computer-aided translation technology in modern translation practice have attracted more attention than ever before.

“Machine translation, also known as automatic translation, is the process of converting a natural language (source language) into another natural language (target language). It is a branch of computational linguistics, which involves computer, cognitive science, linguistics, information theory and other disciplines.” (Bao, 2017: 21) Meanwhile, it is one of the ultimate goals of artificial intelligence. At the same time, machine translation has both great importance of scientific research value and prominent pragmatic value. With the rapid development of economy and the Internet, machine translation technology plays an increasingly consequential role in promoting political, economic and cultural exchanges.

剩余内容已隐藏，请支付后下载全文，论文总字数：25448字