Machine translation systems are conventionally trained on textual resources that do not model phenomena that occur in spoken language. While the evaluation of neural machine translation systems on textual inputs is actively researched in the literature, little has been discovered about the complexities of translating spoken language data with neural models. We introduce and motivate interesting...

We aim to shed light on the strengths and weaknesses of the newly introduced neural machine translation paradigm. To that end, we conduct a multifaceted evaluation in which we compare outputs produced by state-of-the-art neural machine translation and phrase-based machine translation systems for 9 language directions across a number of dimensions. Specifically, we measure the similarity of the ...

This work presents two different translation models using recurrent neural networks. The first one is a word-based approach using word alignments. Second, we present phrase-based translation models that are more consistent with phrasebased decoding. Moreover, we introduce bidirectional recurrent neural models to the problem of machine translation, allowing us to use the full source sentence in ...

Recent research in neural machine translation has largely focused on two aspects; neural network architectures and end-toend learning algorithms. The problem of decoding, however, has received relatively little attention from the research community. In this paper, we solely focus on the problem of decoding given a trained neural machine translation model. Instead of trying to build a new decodi...

When people travel to another country for work or leisure, they regularly need a medium help them understand the written messages in other languages. Google Translate offers new service: translating content of images (texts) instantly and freely into 100 languages powered by Neural Machine Translation approach (NMT). In this vein, current research paper attempts evaluate accuracy Image service ...

The quality of machine translation is rapidly evolving. Today one can find several machine translation systems on the web that provide reasonable translations, although the systems are not perfect. In some specific domains, the quality may decrease. A recently proposed approach to this domain is neural machine translation. It aims at building a jointly-tuned single neural network that maximizes...

Most statistical machine translation (SMT) systems are modeled using a loglinear framework. Although the log-linear model achieves success in SMT, it still suffers from some limitations: (1) the features are required to be linear with respect to the model itself; (2) features cannot be further interpreted to reach their potential. A neural network is a reasonable method to address these pitfall...

Previous work on utilizing parse trees of source sentence in Attentional Neural Machine Translation was promising. However, current models suffer from a major drawback: they use only 1-best parse tree which may lead to translation mistakes due to parsing errors. In this paper we propose a forest-to-sequence Attentional Neural Machine Translation model which uses a forest instead of the 1-best t...

The aim of this paper is the design and development a new English-Arabic neural machine translation (NMT) called DIA system. main purpose designing system to study translator limited sulfur industry domain as stand-alone tool in order improve quality. Machine (MT) are very sensitive domains they were trained on can be integrated with general (English-Arabic) MT systems. proposed has mainly four...