This presentation demonstrates a new multi-engine machine translation system, which combines knowledge-based and example-based machine translation strategies for realtime translation of business news captions from English to German.

Virtualization is already a common technology used in data centers as well as on desktop computers; it gains additional momentum with the spread of cloud computing. In this paper we analyze the performance and behavior of virtual resources in multi virtual machine scenarios running the same workload. We evaluate the performance in terms of CPU, memory and disk IO throughput. In doing so we vary...

In this paper we investigate the problem of adapting a machine translation system to the feedback provided by multiple post-editors. It is well know that translators might have very different post-editing styles and that this variability hinders the application of online learning methods, which indeed assume a homogeneous source of adaptation data. We hence propose multi-task learning to levera...

The existing multi-label support vector machine (Rank-SVM) has an extremely high computational complexity due to a large number of variables in its quadratic programming. When the Frank–Wolfe (FW) method is applied, a large-scale linear programming still needs to be solved at any iteration. Therefore it is highly desirable to design and implement a new efficient SVM-type multi-label algorithm. ...

In this paper, I look at some of the problems of Machine Translation (MT) as compared to multi-lingual text processing and text retrieval. In particular, I discuss the question of the evaluation of the output of MT systems, as opposed to the output of other NLP applications. Finally I raise the question of the political implications of the choice of input and output languages for MT systems wit...

In this thesis, we investigate and extend the phrase-based approach to statistical machine translation. Due to improved concepts and algorithms, the quality of the generated translation hypotheses has been significantly improved in recent years. Still, the translation quality leaves a lot to be desired when going beyond traditional translation tasks, such as newswire articles, and when addressi...

We present a learnt system for multi-view stereopsis. In contrast to recent learning based methods for 3D reconstruction, we leverage the underlying 3D geometry of the problem through feature projection and unprojection along viewing rays. By formulating these operations in a differentiable manner, we are able to learn the system end-to-end for the task of metric 3D reconstruction. End-to-end l...

Recent studies disclose that maximizing the minimum margin like support vector machines does not necessarily lead to better generalization performances, and instead, it is crucial to optimize the margin distribution. Although it has been shown that for binary classification, characterizing the margin distribution by the firstand second-order statistics can achieve superior performance. It still...

Attention-based Encoder-Decoder has the effective architecture for neural machine translation (NMT), which typically relies on recurrent neural networks (RNN) to build the blocks that will be lately called by attentive reader during the decoding process. This design of encoder yields relatively uniform composition on source sentence, despite the gating mechanism employed in encoding RNN. On the...

This paper presents a Tikhonov regularization based piecewise classification model for multi-category discrimination of sets or objects. The proposed model includes a linear classification and nonlinear kernel classification model formulation. Advantages of the regularized multi-classification formulations include its ability to express a multi-class problem as a single and unconstrained optimi...