The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. We present a faster and simpler architecture based on a succession of convolutional layers. This allows to encode the source sentence simultaneously compared to recurrent networks for which computation is constrained by temporal dependencies. On WMT’16 EnglishRomanian translation w...

In this paper, we implement a multilingual Statistical Machine Translation (SMT) system for Arabic-English Translation. Arabic Text can be categorized into standard and dialectal Arabic. These two forms of Arabic differ significantly. Different mono-lingual and multi-lingual hybrid SMT approaches are compared. Mono-lingual systems do always result in better translation accuracy in one Arabic fo...

Movies are everyday entertainment for people in their daily lives. There a lot of foreign movies that being played Indonesian theatres. Unfortunately, there many places where watch the movie with subtitles not created by professional translators. The Social Network was translated more than one translator. This research conducted to analyze how accurate translation is and what similarities diffe...

Important regions of rRNA are rich in nucleotide modifications that can have strong effects on ribosome biogenesis and translation efficiency. Here, we examine the influence of pseudouridylation and 2'-O-methylation on translation accuracy in yeast, by deleting the corresponding guide snoRNAs. The regions analyzed were: the decoding centre (eight modifications), and two intersubunit bridge doma...

We use the left and right monocular motion and structure parameters of two stereo image sequences (direction of translation, relative depth, observer rotation and rotational acceleration) to compute absolute depth, absolute translation and absolute translational acceleration for each pair of left and right images. Individual translation parameters computed at each frame are integrated over time...

As the parallel corpus is not available all the time, pivot language was introduced to solve the parallel corpus sparseness in statistical machine translation. In this paper, we carried out several phrase-based SMT experiments, and analyzed the detailed reasons that caused the decline in translation performance. Experimental results indicated that both covering rate of phrase pairs and translat...

In Statistical Machine Translation, the use of reordering for certain language pairs can produce a significant improvement on translation accuracy. However, the search problem is shown to be NP-hard when arbitrary reorderings are allowed. This paper addresses the question of reordering for an Ngram-based SMT approach following two complementary strategies, namely reordered search and tuple unfo...

Aminoacyl-tRNAs (aa-tRNAs) are selected by the messenger RNA programmed ribosome in ternary complex with elongation factor Tu (EF-Tu) and GTP and then, again, in a proofreading step after GTP hydrolysis on EF-Tu. We use tRNA mutants with different affinities for EF-Tu to demonstrate that proofreading of aa-tRNAs occurs in two consecutive steps. First, aa-tRNAs in ternary complex with EF-Tu·GDP ...

The speed and accuracy of protein synthesis are fundamental parameters for understanding the fitness of living cells, the quality control of translation, and the evolution of ribosomes. In this study, we analyse the speed and accuracy of the decoding step under conditions reproducing the high speed of translation in vivo. We show that error frequency is close to 10⁻³, consistent with the values...

In this paper, we report on an unsupervised greedy-style process for acquiring phrase translations from sentence-aligned parallel corpora. Thanks to innovative selection strategies, this process can acquire multiple translations without size criteria, i.e. phrases can have several translations, can be of any size, and their size is not considered when selecting their translations. Even though t...