الترجمة المتزامنة هي مهمة تبدأ فيها الترجمة قبل انتهاء المتكلم من التحدث، لذلك من المهم أن تقرر متى تبدأ عملية الترجمة.ومع ذلك، فإن اتخاذ قرار بشأن قراءة المزيد من كلمات الإدخال أو بدء الترجمة من الصعب على أزواج اللغة مع أوامر كلمة مختلفة مثل اللغة الإنجليزية واليابانية.بدافع من مفهوم إعادة ترتيب المسبق، نقترح بضع قواعد قرارات بسيطة باستخدام تسمية التأسيس التالي المتوقع من خلال التنبؤ التسمي التأسيسي التدريجي.في تجارب على الترجمة الفورية الإنجليزية إلى اليابانية، الطريقة المقترحة تفوق خطوط الأساس في مفاضلة جودة الكمون.
Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is difficult for language pairs with different word orders such as English and Japanese. Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.
References used
https://aclanthology.org/
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging
In a real-time simultaneous translation setting and neural machine translation (NMT) models start generating target language tokens from incomplete source language sentences and making them harder to translate and leading to poor translation quality.
The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical ent
Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance still lags behind traditional
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource-rich conditions. However, evaluations using real-world lowresource languages still result in unsatisfactory performance. This work prop