محول غير تلقائي هو نموذج توليد نص واعد.ومع ذلك، لا تزال النماذج الحالية غير التلقائية التي لا تزال تقف وراء نظرائها التلقائي في جودة الترجمة.نحن نعزو فجوة الدقة هذه إلى عدم وجود نمذجة التبعية بين مدخلات فك التشفير.في هذه الورقة، نقترح CNAT، والتي تتعلم الرموز الفئوية الضمنية بمثابة متغيرات كامنة في فك التشفير غير التشغيلي التشغيلي.إن التفاعل بين هذه الرموز الفئوية سيلم على التبعيات المفقودة ويحسن القدرة النموذجية.تظهر نتائج التجربة أن نموذجنا يحقق أداء قابلا أو أفضل في مهام الترجمة الآلية من العديد من خطوط الأساس القوية.
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency modeling among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks than several strong baselines.
References used
https://aclanthology.org/
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly modeling dep
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
Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine Translation (AT) k
We present a model to predict fine-grained emotions along the continuous dimensions of valence, arousal, and dominance (VAD) with a corpus with categorical emotion annotations. Our model is trained by minimizing the EMD (Earth Mover's Distance) loss
We consider the problem of learning to repair erroneous C programs by learning optimal alignments with correct programs. Since the previous approaches fix a single error in a line, it is inevitable to iterate the fixing process until no errors remain