Evaluating Free Online Machine Translators in Rendering Persian News Headlines into English: Hutchins and Somers’ Criteria in Focus

  • سال انتشار: 1397
  • محل انتشار: کنفرانس ملی رویکرد های نوین در زبان شناسی کاربردی و مطالعات ترجمه
  • کد COI اختصاصی: SHBUCONF01_020
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 514
دانلود فایل این مقاله

نویسندگان

Zahra Saberi

department of English Isfahan Branch Islamic AzadUniversity, Isfahan,, Iran

Ahmad Ameri-Golestan

Department of english, majlesi branch, islamic azad universiey, majlesi,isfahan. Iran

چکیده

Nowadays, multiple translations are done using the free online machine translation (MT), such as Google Translate, Bing translator, and Babylon. Since these machines are updated regularly by their designers, it seems that evaluating machine translators at regular intervals can be very significant either to the end users or the designers themselves. This study was aimed at examining the translation quality of 3 free online machine translators which offer Persian into English translation services, including Google Translate, Bing Translator, and Babylon. Forty Persian news headlines were randomly selected from Islamic Republic News Agency – IRNA. The news headlines were translated by the three MT systems. A questionnaire was designed and assigned to 30 professionals to compare the outputs with human translations and evaluate the MT systems to determine which system was more effective in translating the news headlines. The evaluation was based on the criteria proposed by Hutchins and Somers (1992): intelligibility, fidelity, and style. The findings indicated that the best machine translator for translating Persian news headlines into English was Google Translate with 91.25% of intelligibility, 84.25% of fidelity, and 87% of style. After Google Translate the best translation was delivered by Babylon with 59.25% of intelligibility, 62.5% of fidelity, and 66.5% of style. Additionally, Bing Translator delivered the lowest scores of 58.25% of intelligibility, 57.75% of fidelity, and 52.25% of style. As implication, the results of this evaluation would help Iranian users make, in advance, an informed choice as to the free online machine translator that meets their needs best when translating Persian news headlines into English.

کلیدواژه ها

Evaluation, Fidelity, Intelligibility, Online Machine Translator, News headlines, Style.

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.