في هذه الورقة، نقدم نهجا جديدا لتكييف المجال في الجهاز العصبي الذي يهدف إلى تحسين جودة Thetranslation على نطاق جديد. إضافة مجالات جديدة هي مهمة عالية تحديا لبيانات الترجمة الآلية العصبية، يصبح أكثر عبادة منتشرةالمجالات الفنية مثل Chem-Istry والذكاء الاصطناعي بسبب مصطلحات Spe-Sicific، إلخ. نقترح أسلوب الترجمة الخلفي العجول Domainspecific والتي تنوع بيانات الأحادية المتوفرة والبيانات الاصطناعية العامة بطريقة مختلفة. هذا النهج يستخدم خارج الكلمات. النهجعام جدا ويمكن أن تقوم بالياف بأي زوج لغة لأي مجال.نقوم بإجراء تجاربنا على الكنديمان والذكاء الاصطناعي) من أجل اللغة الهندية والتيلجو في كل من direc-tions.وقد لوحظ أن استخدام البيانات الاصطناعية الاستخدام التي تم إنشاؤها بواسطة proposedalgorithm يحسن درجات بلو بشكل كبير.
In this paper, we present a novel approachfor domain adaptation in Neural MachineTranslation which aims to improve thetranslation quality over a new domain.Adapting new domains is a highly challeng-ing task for Neural Machine Translation onlimited data, it becomes even more diffi-cult for technical domains such as Chem-istry and Artificial Intelligence due to spe-cific terminology, etc. We propose DomainSpecific Back Translation method whichuses available monolingual data and gen-erates synthetic data in a different way.This approach uses Out Of Domain words.The approach is very generic and can beapplied to any language pair for any domain. We conduct our experiments onChemistry and Artificial Intelligence do-mains for Hindi and Telugu in both direc-tions. It has been observed that the usageof synthetic data created by the proposedalgorithm improves the BLEU scores significantly.
References used
https://aclanthology.org/
We study the problem of domain adaptation in Neural Machine Translation (NMT) when domain-specific data cannot be shared due to confidentiality or copyright issues. As a first step, we propose to fragment data into phrase pairs and use a random sampl
In this paper, we describe our MiSS system that participated in the WMT21 news translation task. We mainly participated in the evaluation of the three translation directions of English-Chinese and Japanese-English translation tasks. In the systems su
The neural machine translation approach has gained popularity in machine translation because of its context analysing ability and its handling of long-term dependency issues. We have participated in the WMT21 shared task of similar language translati
Incorporating multiple input modalities in a machine translation (MT) system is gaining popularity among MT researchers. Unlike the publicly available dataset for Multimodal Machine Translation (MMT) tasks, where the captions are short image descript
This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selec