The most popular video website YouTube has about 2 billion users worldwide who speak and understand different languages. Subtitles are essential for the to get message from video. However, not all owners provide subtitles their videos. It causes potential audiences have difficulties in understanding content. Thus, this study proposed a speech recorder translator solve problem. general concept o...

This paper describes the statistical machine translation system developed at RWTH Aachen University for the English→Romanian translation task of the ACL 2016 First Conference on Machine Translation (WMT 2016). We combined three different state-ofthe-art systems in a system combination: A phrase-based system, a hierarchical phrase-based system and an attentionbased neural machine translation sys...

Neural machine translation (NMT) with recurrent neural networks, has proven to be an effective technique for end-to-end machine translation. However, in spite of its promising advances over traditional translation methods, it typically suffers from an issue of unbalanced outputs, that arise from both the nature of recurrent neural networks themselves, and the challenges inherent in machine tran...

In this paper, we propose a novel recursive recurrent neural network (R2NN) to model the end-to-end decoding process for statistical machine translation. R2NN is a combination of recursive neural network and recurrent neural network, and in turn integrates their respective capabilities: (1) new information can be used to generate the next hidden state, like recurrent neural networks, so that la...

Recently, neural network models have achieved consistent improvements in statistical machine translation. However, most networks only use one-hot encoded input vectors of words as their input. In this work, we investigated the exponentially decaying bag-of-words input features for feed-forward neural network translation models and proposed to train the decay rates along with other weight parame...