This paper presents an overview of the system submitted by the University of Hamburg to the IT domain shared translation task as part of the ACL 2016 First Conference of Machine Translation (WMT 2016). We have chosen data selection as a domain adaptation method. The filtering of the general domain data makes use of paragraph vectors as a novel approach for scoring the sentences. Experiments wer...

The contribution reports on an evaluation of efforts to improve MT quality by domain adaptation, for both rule-based and statistical MT, as done in the ACCURAT project (Skadiņa et al. 2012). Comparative evaluation shows an increase of about 5% for both MT paradigms after system adaptation; absolute evaluation shows an increase in adequacy and fluency for SMT. While the RMT solution is superior ...

Amulti source domain adaptation based learning for addressing subject based variability in myoelectric signals (SEMG), enabling generalized framework for detecting

Cross language classification is an important task in multilingual learning, aiming for reducing the labeling cost of training a different classification model for each individual language. In this paper we develop a novel subspace co-regularized multi-view learning method for cross language text classification. The empirical study on a set of cross language text classification tasks shows the ...

An information extraction system is designed to operate over a specific domain, and cannot be applied to new domains without being adapted if it is to perform well. We will investigate the problem of adapting information extraction systems to new domains by first defining the task of information extraction and giving an example of an information extraction system. We will then outline the modul...

In this work, we present a method for unsupervised domain adaptation (UDA), where we aim to transfer knowledge from a label-rich domain (i.e., a source domain) to an unlabeled domain (i.e., a target domain). Many adversarial learning methods have been proposed for this task. These methods train domain classifier networks (i.e., a discriminator) to discriminate distinguish the features as either...

Popular techniques for domain adaptation such as the feature augmentation method of Daumé III (2009) have mostly been considered for sparse binary-valued features, but not for dense realvalued features such as those used in neural networks. In this paper, we describe simple neural extensions of these techniques. First, we propose a natural generalization of the feature augmentation method that ...

Domain adaptation is transfer learning which aims to generalize a learning model across training and testing data with different distributions. Most previous research tackle this problem in seeking a shared feature representation between source and target domains while reducing the mismatch of their data distributions. In this paper, we propose a close yet discriminative domain adaptation metho...

A fundamental assumption for any machine learning task is to have training and test data instances drawn from the same distribution while having a sufficiently large number of training instances. In many practical settings, this ideal assumption is invalidated as the labeled training instances are scarce and there is a high cost associated with labeling them. On the other hand, we might have ac...

Non-invasive myoelectric prostheses require a long training time to obtain satisfactory control dexterity. These training times could possibly be reduced by leveraging over training efforts by previous subjects. So-called domain adaptation algorithms formalize this strategy and have indeed been shown to significantly reduce the amount of required training data for intact subjects for myoelectri...