Beta
208437

Out of the BLEU: An Error Analysis of Statistical and Neural Machine Translation of WikiHow Articles from English into Arabic

Article

Last updated: 25 Dec 2024

Subjects

-

Tags

-

Abstract

Most studies that compare the quality of Neural Machine Translation (NMT) to that of Statistical Machine Translation (SMT) rely on automatic evaluation methods, mainly the bilingual evaluation understudy (BLEU), without performing any kind of human assessment. While BLEU is a good indicator of the overall performance of MT systems, it does not offer any detailed linguistic insights into the types of errors generated by those MT models. Such insights are crucial for researchers to identify areas for improvement and for language service providers to understand how upgrading to NMT gives them better results. This paper breaks free from BLEU by conducting an error analysis that compares the performance of Google SMT and NMT engines for English-into-Arabic translation. The corpus consists of six WikiHow articles. The analysis is guided by the DQF-MQM Harmonized Error Typology which classifies translation errors into eight major categories, namely, accuracy, fluency, terminology, style, design, locale convention, verity and other (for any other issues). A fine-grained classification of translation errors as such enables the researcher to explore the error types generated by each MT model, the error types eliminated by NMT, and the new error types introduced by NMT. The paper focuses on the English-Arabic language pair because it is one of the least studied pairs in the comparative literature of SMT and NMT. The results show that NMT generates less grammatical errors and mistranslations than SMT. NMT output is more fluent and robust. However, SMT is more consistent with translating proper nouns and out-of-vocabulary words.

DOI

10.21608/opde.2021.208437

Keywords

DQF-MQM harmonized error typology, neural machine translation, Statistical machine translation, Translation Quality Assessment

Authors

First Name

Nessma

Last Name

Diab

MiddleName

-

Affiliation

-

Email

nesma_diab@alsun.asu.edu.eg

City

-

Orcid

-

Volume

75

Article Issue

1

Related Issue

29333

Issue Date

2021-07-01

Receive Date

2021-12-09

Publish Date

2021-07-01

Page Start

181

Page End

211

Print ISSN

1110-2721

Online ISSN

2735-3591

Link

https://opde.journals.ekb.eg/article_208437.html

Detail API

https://opde.journals.ekb.eg/service?article_code=208437

Order

8

Type

Original Article

Type Code

1,140

Publication Type

Journal

Publication Title

CDELT Occasional Papers in the Development of English Education

Publication Link

https://opde.journals.ekb.eg/

MainTitle

Out of the BLEU: An Error Analysis of Statistical and Neural Machine Translation of WikiHow Articles from English into Arabic

Details

Type

Article

Created At

22 Jan 2023