تعلم الترجمة الآلية العصبية متعددة اللغات (MNMT) ترجمة أزواج متعددة اللغات بنموذج واحد، يحتمل أن يحسن كل من الدقة وكفاءة الذاكرة للنماذج المنتشرة. ومع ذلك، فإن عدم اختلال البيانات الثقيلة بين اللغات يعوق النموذج من الأداء بشكل موحد عبر أزواج اللغة. في هذه الورقة، نقترح هدفا تعليميا جديدا ل MNMT بناء على التحسين القوي التويضي، مما يقلل من الخسارة المتوقعة الأسوأ في مجموعة أزواج اللغة. نوضح كذلك كيفية تحسين هذا الهدف من الناحية العملية للترجمة الكبيرة باستخدام مخطط أفضل استجابة مزخرف، وهو فعاليتان فعالة وتتحمل تكلفة حسابية إضافية ضئيلة مقارنة بقليل المخاطر التجريبية القياسية. نقوم بإجراء تجارب مكثفة على ثلاث مجموعات من اللغات من مجموعة بيانات وتظهر أن طريقتنا تتفوق باستمرار على أساليب خطية قوية من حيث المتوسط والأداء لكل لغة تحت كلا من إعدادات الترجمة متعددة إلى واحدة وواحدة متعددة.
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 hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
References used
https://aclanthology.org/
Traditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications. We aim to adapt translation models to speech by introducing actual lexical errors from ASR and segment
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
Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-sou
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
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translat