We describe a machine translation approach being designed at HKUST to integrate semantic processing into statistical machine translation, beginning with entity and word sense disambiguation. We show how integrating the semantic modules consistently improves translation quality across several data sets. We report results on five different IWSLT 2006 speech translation tasks, representing HKUST’s...

Accurate acquisition and effective translation of customer requirements are two key links in product configuration design. In the paper, two concepts are introduced for customer requirement decomposition. One is the requirement element, and the other is the granularity of requirement element. Moreover, the controlling principle for granularity of requirement element is given and the method of r...

This paper proposes an approximate ontology translation framework for coordinating heterogeneous information services such as regional information services. To achieve semantic interoperability in heterogeneous information services, ontologies have been widely used. Translation of multiple ontologies is necessary for a domain with cross-cultural aspects, such as regional information services. O...

In this article some of the problems encountered in designing an evaluation for the MIROSLAV machine translation (MT) system will be examined. We will concentrate mainly on the strategies employed in the evaluation and the evaluation areas, namely translation quality and translation productivity, whereas the former will be treated in more detail than the latter. In conclusion we will present tw...

Image-to-image translation is the recent trend to transform images from one domain another using a generative adversarial network (GAN). The existing GAN models perform training by only utilizing input and output modalities of transformation. In this paper, we semantic injected models. Specifically, train with original inject few epochs for map. Let us refer as image into target domain. injecti...

We collected number-of-translation norms on 562 Dutch-English translation pairs from several previous studies of cross-language processing. Participants were highly proficient Dutch-English bilinguals. Form and semantic similarity ratings were collected on the 1,003 possible translation pairs. Approximately 40% of the translations were rated as being similar across languages with respect to spe...