Large-scale parallel corpora are indispensable to train highly accurate machine translators. However, manually constructed large-scale parallel corpora are not freely available in many language pairs. In previous studies, training data have been expanded using a pseudoparallel corpus obtained using machine translation of the monolingual corpus in the target language. However, in lowresource lan...

In this paper, we describe our submissions to the WMT17 Multimodal Translation Task. For Task 1 (multimodal translation), our best scoring system is a purely textual neural translation of the source image caption to the target language. The main feature of the system is the use of additional data that was acquired by selecting similar sentences from parallel corpora and by data synthesis with b...

In this paper, we describe our submissions to the WMT17 Multimodal Translation Task. For Task 1 (multimodal translation), our best scoring system is a purely textual neural translation of the source image caption to the target language. The main feature of the system is the use of additional data that was acquired by selecting similar sentences from parallel corpora and by data synthesis with b...

It is well known that statistical machine translation systems perform best when they are adapted to the task. In this paper we propose new methods to quickly perform incremental adaptation without the need to obtain word-by-word alignments from GIZA or similar tools. The main idea is to use an automatic translation as pivot to infer alignments between the source sentence and the reference trans...

We propose a method of constructing an example-based machine translation (EBMT) system that exploits a content-aligned bilingual corpus. First, the sentences and phrases in the corpus are aligned across the two languages, and the pairs with high translation confidence are selected and stored in the translation memory. Then, for a given input sentences, the system searches for fitting examples b...

In proteomics, to find the genomic localization of a gene, a protein may be interpreted back to its DNA/mRNA using the method of reverse translation. A particular amino acid may be translated into more than one codon as the uncertainties exist in the reverse translation of a protein. In this paper, we propose a Bernoulli process approximation based on the usage of frequency distribution for the...