غالبا ما يتم الحصول على بيانات التدريب للترجمة الآلية (MT) من العديد من الشركات الكبيرة التي هي متعددة الأوجه في الطبيعة، على سبيل المثالتحتوي على محتويات من مجالات متعددة أو مستويات مختلفة من الجودة أو التعقيد.بطبيعة الحال، لا تحدث هذه الجوانب بتردد متساو ولا هي نفسها نفسها بنفس القدر لسيناريو الاختبار في متناول اليد.في هذا العمل، نقترح تحسين هذا التوازن بشكل مشترك مع معلمات نموذج MT لتخفيف مطوري النظام من تصميم الجدول اليدوي.يتم تدريب عصري متعدد المسلح على الاختيار ديناميكيا بين الجوانب بطريقة مفيدة لنظام MT.نقيمها على ثلاثة تطبيقات مختلفة متعددة الأوجه: موازنة البيانات النسبية والبيانات التدريبية الطبيعية، أو البيانات من مجالات متعددة أو أزواج متعددة اللغات.نجد أن تعلم الفرعيد يؤدي إلى أنظمة MT تنافسية عبر المهام، ويقدم تحليلنا رؤى في استراتيجياته المستفادة ومجموعات البيانات الأساسية.
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity. Naturally, these facets do not occur with equal frequency, nor are they equally important for the test scenario at hand. In this work, we propose to optimize this balance jointly with MT model parameters to relieve system developers from manual schedule design. A multi-armed bandit is trained to dynamically choose between facets in a way that is most beneficial for the MT system. We evaluate it on three different multi-facet applications: balancing translationese and natural training data, or data from multiple domains or multiple language pairs. We find that bandit learning leads to competitive MT systems across tasks, and our analysis provides insights into its learned strategies and the underlying data sets.
References used
https://aclanthology.org/
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
When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of re
This research deals with the importance of trade in the Levant, through the site, which produced the important commercial cities prominent, and displays the influence of Bedouin negatively and positively in the movement of trade and the danger to the movement of goods and the reputation of the state. And the impact of the road sector and the damage toll they trade, taking advantage of the geographical nature of the Levant.
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without expli
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages