وجدت خوارزميات التدرج السياسي اعتماد واسع في NLP، لكنها أصبحت مؤخرا عرضة للنقد، مما يشك في ملاءمتها ل NMT.تشوشين وآخرون.(2020) حدد نقاط ضعف متعددة والشك في تحديد نجاحهم من خلال شكل توزيعات الإخراج بدلا من المكافأة.في هذه الورقة، نلتأكيد هذه المطالبات ودراسةها تحت مجموعة أوسع من التكوينات.تكشف تجاربنا على التكيف في المجال والمجال عبر المجال أهمية الاستكشاف والمكافآت، وتوفير الأدلة المضادة التجريبية لهذه المطالبات.
Policy gradient algorithms have found wide adoption in NLP, but have recently become subject to criticism, doubting their suitability for NMT. Choshen et al. (2020) identify multiple weaknesses and suspect that their success is determined by the shape of output distributions rather than the reward. In this paper, we revisit these claims and study them under a wider range of configurations. Our experiments on in-domain and cross-domain adaptation reveal the importance of exploration and reward scaling, and provide empirical counter-evidence to these claims.
References used
https://aclanthology.org/
Non-autoregressive neural machine translation, which decomposes the dependence on previous target tokens from the inputs of the decoder, has achieved impressive inference speedup but at the cost of inferior accuracy. Previous works employ iterative d
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of easy'' samples from training data at the early training stage. This is not always achievable for low-resource languages where the amoun
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
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
Interactive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in active learning (AL) exist to upd