تعتمد معظم نماذج الترجمة الآلية العصبية الحالية ترتيب فك التشفير الرخيصي إما من اليسار إلى اليمين أو اليمين إلى اليسار.في هذا العمل، نقترح طريقة رواية تنفصل قيود أوامر فك التشفير هذه، تسمى فك تشفير الذكية.وبشكل أكثر تحديدا، تتوقع طريقةنا أولا كلمة متوسط.يبدأ فك شفرة الكلمات الموجودة على الجانب الأيمن من الكلمة المتوسطة ثم يولد كلمات على اليسار.نحن نقيم طريقة فك التشفير الذكية المقترحة على ثلاث مجموعات البيانات.تظهر النتائج التجريبية أن الطريقة المقترحة يمكن أن تتفوق بشكل كبير على النماذج الأساسية القوية.
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. More specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.
References used
https://aclanthology.org/
Neural machine translation (NMT) models are data-driven and require large-scale training corpus. In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for some extreme
Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the g
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
Recent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this research line and propose a novel substitute