Abstract Machine translation (MT) is a technique that leverages computers to translate
human languages automatically. Nowadays, neural machine translation (NMT) which …

The large attention-based encoder-decoder network (Transformer) has become prevailing
recently due to its effectiveness. But the high computation complexity of its decoder raises …

8-bit integer inference, as a promising direction in reducing both the latency and storage of
deep neural networks, has made great progress recently. On the other hand, previous …

Scene text recognition is a crucial area of research in computer vision. However, current
mainstream scene text recognition models suffer from incomplete feature extraction due to …

Non-autoregressive architecture for neural text-to-speech (TTS) allows for parallel
implementation, thus reduces inference time over its autoregressive counterpart. However …

Quality problem-solving (QPS) is one of the most important processes to ensure product
quality. In the context of Industry 4.0, increasingly more manufacturing companies have …

With the rapid development of globalization, the demand for translation between different
languages is also increasing. Although pre-training has achieved excellent results in neural …

Smart contracts are rapidly applied in many fields, with their varied types and increasing
complexity. A sharp increase in the method development demands seems to be certain …

This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency
Shared Task. We focus on the efficient implementation of deep Transformer models\cite …

This paper proposes a novel approach, Source Language Prediction-Language Model for
Neural Machine Translation (SLP-LMNMT), based on the UNILM's sequence-to-sequence …