Extending BLEU Evaluation Method with Linguistic Weight

Yang, Muyun; Zhu, Jigui; Li, Jufeng; Wang, Lixin; Qi, Haoliang; Li, Sheng; Liu, Daxin

doi:10.1109/icycs.2008.362

Cited by 14 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BLEU evaluation method is language independent and can be used to assess any natural language. Reference [8] shows that conducted in Extending BLEU Evaluation Method with Linguistics Weight research to improve the effectiveness of BLEU method, and they succeeded through the use of multiple Ngram weights. Reference [9] evaluates 2-way Iraqi Arabic-English speech translation systems using automated metrics.…”

Section: Review Of Relevant Literaturementioning

confidence: 99%

Assessing the Translation of Google and Microsoft Bing in Translating Political Texts from Arabic into English

Almahasees¹

2017

IJLLL

View full text Add to dashboard Cite

Abstract-Online machine translation (OMT) systems are widely used throughout the world freely or at low cost. Most of these systems use statistical machine translation (SMT) that is based on a corpus full with translation examples to learn from them how to translate correctly. Online automatic machine translation systems differ widely in their effectiveness and accuracy. Therefore, the wide spread of such translation platforms make it necessary to evaluate the output in order to shed light on the capacity and usability of each system. The present study have selected the most prominent translation systems, Google and Microsoft to test which system is better and more reliable in rendering English<>Arabic translation. To conduct the study, the researcher has chosen automatic evaluation of the two system outputs by using the most popular automatic evacuation metric BLEU. The study's corpus consists of 25 Arabic sentences extracted from Petra News Agency of Jordan with its human reference translation from the English version of Petra. The result of the research showed that Google translate achieves better results than Microsoft Bing in comparison to human referenced translation. However, Machine Translation (MT) is still far from reaching fully automatic translation of a quality obtained by human translators.

show abstract

Section: Review Of Relevant Literaturementioning

confidence: 99%

Assessing the Translation of Google and Microsoft Bing in Translating Political Texts from Arabic into English

Almahasees¹

2017

IJLLL

View full text Add to dashboard Cite

show abstract

“…Another proposed extended BLEU method is presented in a study conducted by Yang, Zhu, Li, Wang, Qi, Li and Daxin [19]. They proposed assigning different weights to different part-of-speech (POS) and different lengths of n-gram.…”

Section: Related Workmentioning

confidence: 99%

Comparative Study Between METEOR and BLEU Methods of MT: Arabic into English Translation as a Case Study

Hadla¹,

Hailat²,

Al-Kabi³

2015

ijacsa

View full text Add to dashboard Cite

Abstract-The Internet provides its users with a variety of services, and these services include free online machine translators, which translate free of charge between many of the world's languages such as Arabic, English, Chinese, German, Spanish, French, Russian, etc. Machine translators facilitate the transfer of information between different languages, thus eliminating the language barrier, since the amount of information and knowledge available varies from one language to another, Arabic content on the internet, for example, accounts 1% of the total internet content, while Arabs constitute 5% of the population of the earth, which means that the intellectual productivity of the Arabs is low because within internet use Internet's Arabic content represents 20% of their natural proportion, which in turn encouraged some Arab parties to improve Arabic content within the internet. So, many of those interested specialists rely on machine translators to bridge the knowledge gap between the information available in the Arabic language and those in other living languages such as English.This empirical study aims to identify the best Arabic to English Machine translation system, in order to help the developers of these systems to enhance the effectiveness of these systems. Furthermore, such studies help the users to choose the best. This study involves the construction of a system for Automatic Machine Translation Evaluation System of the Arabic language into language. This study includes assessing the accuracy of the translation by the two known machine translators, Google Translate, and the second, which bears the name of Babylon machine translation from Arabic into English. BLEU and METEOR methods are used the MT quality, and to identify the closer method to human judgments. The authors conclude that BLEU is closer to human judgments METEOR method.

show abstract

“…BLEU has a number of cons, therefore a number of researchers have attempted to enhance this important method. One of such attempts was conducted by Yang et al [12]. They have used linguistic features of the evaluated sentences outputted from the machine translation systems in their enhancements.…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluating English to Arabic Machine Translation Using BLEU

Al-Kabi¹,

Hailat²,

Al-Shawakfa³

et al. 2013

IJACSA

View full text Add to dashboard Cite

Abstract-This study aims to compare the effectiveness of two popular machine translation systems (Google Translate and Babylon machine translation system) used to translate English sentences into Arabic relative to the effectiveness of English to Arabic human translation. There are many automatic methods used to evaluate different machine translators, one of these methods; Bilingual Evaluation Understudy (BLEU) method, which was adopted and implemented to achieve the main goal of this study. BLEU method is based on the assumptions of automated measures that depend on matching machine translators' output to human reference translations; the higher the score, the closer the translation to the human translation will be. Well known English sayings in addition to manually collected sentences from different Internet web sites were used for evaluation purposes. The results of this study have showed that Google machine translation system is better than Babylon machine translation system in terms of precision of translation from English to Arabic.

show abstract

Extending BLEU Evaluation Method with Linguistic Weight

Cited by 14 publications

References 6 publications

Assessing the Translation of Google and Microsoft Bing in Translating Political Texts from Arabic into English

Assessing the Translation of Google and Microsoft Bing in Translating Political Texts from Arabic into English

Comparative Study Between METEOR and BLEU Methods of MT: Arabic into English Translation as a Case Study

Evaluating English to Arabic Machine Translation Using BLEU

Contact Info

Product

Resources

About