تعاني ترجمة الآلات العصبية التي تعتمد على نص ثنائي اللغة مع بيانات تدريبية محدودة من التنوع المعجمي، والتي تقلل من دقة ترجمة الكلمات النادرة وتقلص من تعميم نظام الترجمة.في هذا العمل، نستخدم التسميات التوضيحية المتعددة من مجموعة بيانات متعددة 30 ألفا لزيادة التنوع المعجمي بمساعدة النقل عبر اللغات للمعلومات بين اللغات في إعداد متعدد اللغات.في هذا الإعداد المتعدد اللغات والعددية، فإن إدراج الميزات المرئية يعزز جودة الترجمة بهامش كبير.تؤكد الدراسة التجريبية أن نهجنا متعدد الوسائط المقترح يحقق مكسبا كبيرا من حيث النتيجة التلقائية ويظهر متانة في التعامل مع ترجمة الكلمات النادرة بذريعة مهام الترجمة الهندية والتيلجو.
Neural machine translation based on bilingual text with limited training data suffers from lexical diversity, which lowers the rare word translation accuracy and reduces the generalizability of the translation system. In this work, we utilise the multiple captions from the Multi-30K dataset to increase the lexical diversity aided with the cross-lingual transfer of information among the languages in a multilingual setup. In this multilingual and multimodal setting, the inclusion of the visual features boosts the translation quality by a significant margin. Empirical study affirms that our proposed multimodal approach achieves substantial gain in terms of the automatic score and shows robustness in handling the rare word translation in the pretext of English to/from Hindi and Telugu translation tasks.
References used
https://aclanthology.org/
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search base
Multi-modal machine translation (MMT) aims at improving translation performance by incorporating visual information. Most of the studies leverage the visual information through integrating the global image features as auxiliary input or decoding by a
Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each corpus in
Production NMT systems typically need to serve niche domains that are not covered by adequately large and readily available parallel corpora. As a result, practitioners often fine-tune general purpose models to each of the domains their organisation
Machine translation performs automatic translation from one natural language to another. Neural machine translation attains a state-of-the-art approach in machine translation, but it requires adequate training data, which is a severe problem for low-